© 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. 14774
    Prev
    Next
    INDEX
    Explanations

    words that connect people, events, and descriptions of actions or status together in context

    oai_token-act-pair · gemini-2.0-flash

    made

    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
    .
    -2.94
    .”
    -1.47
    ."
    -1.40
    .).
    -1.34
    .)
    -1.27
    .}
    -1.27
    .");
    -1.27
    .”.
    -1.25
    .’
    -1.23
    .'
    -1.22
    POSITIVE LOGITS
    OGND
    0.81
     tartalomajánló
    0.69
    GHIJKLM
    0.54
    PreferredItem
    0.53
    ENEZ
    0.50
    aguya
    0.47
    GEBURTS
    0.47
    expandindo
    0.47
    ็จ
    0.47
     '{@
    0.47
    Activations Density 31.082%

    No Known Activations