© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4649
    Prev
    Next
    INDEX
    Explanations

    hexadecimal values, technical terms, and abbreviation-like constructs

    oai_token-act-pair · gemini-2.0-flash

    technical descriptions

    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
     onResponse
    -0.39
     DCP
    -0.39
     combineReducers
    -0.35
    NOPQRST
    -0.35
    });*/
    -0.34
    hall
    -0.34
    son
    -0.33
    man
    -0.33
     decembrie
    -0.33
    ('.');
    -0.33
    POSITIVE LOGITS
    nadequate
    0.84
    nappropriate
    0.81
    omenclature
    0.80
    liminary
    0.80
    pportun
    0.79
    pointment
    0.79
    vanced
    0.78
    drawal
    0.77
    ficulty
    0.77
    ilibrium
    0.77
    Activations Density 28.821%

    No Known Activations