© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11341
    Prev
    Next
    INDEX
    Explanations

    uppercase Ch at the beginning of a word

    oai_token-act-pair · gemini-2.0-flash

    tokens starting with 'Ch'

    np_token-act-pair-logits · gpt-4o-mini

    Ch

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    std
    -0.46
    chan
    -0.45
    medes
    -0.44
     future
    -0.43
     prises
    -0.43
     leader
    -0.43
    不忘
    -0.42
    గ
    -0.42
    usleep
    -0.42
     Standards
    -0.42
    POSITIVE LOGITS
     CreateTagHelper
    0.77
    AddTagHelper
    0.71
    parsedMessage
    0.65
    osoba
    0.65
     nephe
    0.64
    ыгана
    0.58
    PreferredItem
    0.57
     Roskov
    0.57
     intStringLen
    0.57
     Réponses
    0.56
    Activations Density 0.252%

    No Known Activations