© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15008
    Prev
    Next
    INDEX
    Explanations

    the prefix "inter", especially in the context of "interfaith", "interfere", "intergenerational", "interrelated", "inter-"

    oai_token-act-pair · gemini-2.0-flash

    occurrences of 'inter'

    np_token-act-pair-logits · gpt-4o-mini

    inter

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.95
    webElementXpaths
    -0.86
    tagHelperRunner
    -0.85
     незавершена
    -0.82
     disambiguazione
    -0.79
    MigrationBuilder
    -0.77
     ujednoznacz
    -0.76
     насељу
    -0.75
     wireType
    -0.69
    Enllaces
    -0.69
    POSITIVE LOGITS
     Gent
    0.44
    ia
    0.42
     nhất
    0.42
    Gent
    0.41
    ios
    0.41
    ex
    0.41
    Cluster
    0.40
    club
    0.39
    gente
    0.39
    io
    0.39
    Activations Density 0.369%

    No Known Activations