© 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. 6835
    Prev
    Next
    INDEX
    Explanations

    words having to do with the narrator's personal history and education, especially schools

    oai_token-act-pair · gemini-2.0-flash

    school/education

    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
    school
    -0.81
    School
    -0.78
     School
    -0.78
     school
    -0.68
     SCHOOL
    -0.68
    SCHOOL
    -0.65
     okuyayım
    -0.53
    Sekolah
    -0.52
     Schools
    -0.52
    College
    -0.52
    POSITIVE LOGITS
    resave
    0.58
    Географи
    0.58
    +#+#
    0.57
    UnknownFieldSet
    0.56
    EndGlobalSection
    0.56
     myſelf
    0.52
    öyle
    0.52
     Brewster
    0.50
     Clovis
    0.50
     Montmartre
    0.49
    Activations Density 4.729%

    No Known Activations