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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3675
    Prev
    Next
    INDEX
    Explanations

    Lithuanian language and proper nouns associated with Lithuanian history and geography especially in the context of the second world war.

    oai_token-act-pair · gemini-2.0-flash

    Contains the character "ſ"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Roskov
    -0.67
    findpost
    -0.61
     esternos
    -0.59
    dent
    -0.52
    TintMode
    -0.48
    oredCriteria
    -0.48
     насељу
    -0.48
    fjspx
    -0.47
     مشين
    -0.47
    Portail
    -0.46
    POSITIVE LOGITS
     pleaſure
    0.68
     chofe
    0.68
     ſeveral
    0.67
     purpoſe
    0.66
     myſelf
    0.66
     Majefty
    0.65
     raiſ
    0.65
     Reſ
    0.60
     Shakspeare
    0.60
     feveral
    0.59
    Activations Density 0.138%

    No Known Activations