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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3814
    Prev
    Next
    INDEX
    Explanations

    code snippets and spanish words related to some kind of conditional

    oai_token-act-pair · gemini-2.0-flash

    Code and Spanish text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     be
    -0.96
     سكانية
    -0.75
     متعلقه
    -0.73
     виправивши
    -0.71
     كومونز
    -0.67
    Be
    -0.66
     disambiguazione
    -0.66
     Be
    -0.64
     חיצוניים
    -0.63
    featureID
    -0.63
    POSITIVE LOGITS
     vaya
    0.60
     desee
    0.56
     mantenga
    0.53
     lleve
    0.52
     vean
    0.51
     vayan
    0.50
     ayude
    0.50
     hayas
    0.50
     seleccione
    0.49
     encuentre
    0.49
    Activations Density 0.742%

    No Known Activations