© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3042
    Prev
    Next
    INDEX
    Explanations

    question words such as "is", "are", "does", "can", "how", "what", and "should"

    oai_token-act-pair · gemini-2.0-flash

    questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Geplaatst
    -0.81
    IndentedString
    -0.80
     يتيمه
    -0.78
    ]();
    -0.76
     sumpay
    -0.75
    IntoConstraints
    -0.74
     AttributeSet
    -0.74
    SharedCtor
    -0.72
    writeFieldEnd
    -0.68
     Uncategorized
    -0.68
    POSITIVE LOGITS
    <bos>
    1.66
    '
    0.56
    are
    0.56
    ’
    0.55
     هل
    0.54
     apakah
    0.53
    ?
    0.51
     האם
    0.47
     still
    0.47
    i
    0.47
    Activations Density 0.233%

    No Known Activations