© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 612
    Prev
    Next
    INDEX
    Explanations

    mixed sentiment, good things with bad things.

    oai_token-act-pair · gemini-2.0-flash

    online content

    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
     For
    -1.77
    For
    -1.74
    FOR
    -1.70
     FOR
    -1.50
     Für
    -1.13
     Pour
    -1.13
     cho
    -1.05
     För
    -1.05
     Για
    -1.03
    ForRow
    -1.02
    POSITIVE LOGITS
    Архівовано
    0.69
    $.
    0.63
     itſelf
    0.63
    Portály
    0.59
     doubtnut
    0.58
     PLWABN
    0.58
    __':
    0.57
    новништво
    0.56
     stiefel
    0.56
     Pozna
    0.55
    Activations Density 4.189%

    No Known Activations