© 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. 14582
    Prev
    Next
    INDEX
    Explanations

    the word "character(s)", and pronouns "his/my/me/I", and words that come before and after

    oai_token-act-pair · gemini-2.0-flash

    character development

    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
     characters
    -2.94
     Characters
    -2.77
     character
    -2.70
     Character
    -2.66
    characters
    -2.58
    Characters
    -2.53
    Character
    -2.52
    character
    -2.48
     CHARACTER
    -2.38
     CHARACTERS
    -2.34
    POSITIVE LOGITS
    хь
    0.51
    ือ
    0.45
    TintMode
    0.45
    دانشنامهٔ
    0.43
     HttpNotFound
    0.42
    ')")
    0.41
    stätten
    0.40
    SequentialGroup
    0.40
     pipelines
    0.40
    ⎦
    0.40
    Activations Density 2.995%

    No Known Activations