© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12145
    Prev
    Next
    INDEX
    Explanations

    hyphenated words starting with "self"

    oai_token-act-pair · gemini-2.0-flash

    self

    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
    OCCURRED
    -0.69
     vuitton
    -0.55
     Sirs
    -0.47
    enderror
    -0.46
     MyBatis
    -0.46
    therin
    -0.46
     smtplib
    -0.46
    toMatchSnapshot
    -0.46
    lgari
    -0.45
     AppBundle
    -0.45
    POSITIVE LOGITS
    Pratique
    0.66
    setting
    0.65
    studied
    0.64
     iconFacebook
    0.63
    developed
    0.63
     betre
    0.61
    PARATION
    0.60
    preservation
    0.60
    preparation
    0.59
    served
    0.59
    Activations Density 4.111%

    No Known Activations