© 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. 3214
    Prev
    Next
    INDEX
    Explanations

    phrases like "hard to" or "difficult to"

    oai_token-act-pair · gemini-2.0-flash

    to

    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
    <bos>
    -1.12
    '
    -0.45
    }))
    -0.43
    GeoNames
    -0.42
    to
    -0.41
    }));
    -0.41
     to
    -0.41
    Бележки
    -0.40
     conhe
    -0.40
    ')]
    -0.39
    POSITIVE LOGITS
     HasFactory
    0.88
    thâu
    0.86
     AssemblyCulture
    0.83
    EDEFAULT
    0.81
    ContentAsync
    0.79
     صوتيه
    0.79
     виправивши
    0.77
    addContainerGap
    0.76
    WebVitals
    0.76
    rrggbb
    0.75
    Activations Density 0.609%

    No Known Activations