© 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. 6645
    Prev
    Next
    INDEX
    Explanations

    strings of hexadecimal characters, often in the format of IDs

    oai_token-act-pair · gemini-2.0-flash

    -

    np_max-act-logits · gemini-2.0-flash

    - Method used: 1 — because every max activating token is "-" — "-"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    9
    -1.52
    8
    -1.43
     ninth
    -1.34
     nine
    -1.30
     eighth
    -1.26
     Ninth
    -1.19
     Nine
    -1.16
     Eighth
    -1.12
     eight
    -1.09
    9
    -1.05
    POSITIVE LOGITS
     jspb
    0.60
    WithIOException
    0.60
    twimg
    0.54
    IsContent
    0.53
     resourceCulture
    0.53
    AnimationsModule
    0.52
     ModelExpression
    0.50
     snippetHide
    0.49
     gyhoeddwyd
    0.49
    省市镇
    0.49
    Activations Density 3.671%

    No Known Activations