© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 437
    Prev
    Next
    INDEX
    Explanations

    capitalized last names within text that contains academic citations or proper names in a food setting

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    SourceChecksum
    -0.79
    ConstraintMaker
    -0.75
    OCCURRED
    -0.70
    bbene
    -0.69
    oredCriteria
    -0.69
    ppure
    -0.69
    ⓧ
    -0.68
     мәкал
    -0.68
    verwijspagina
    -0.66
     feroit
    -0.65
    POSITIVE LOGITS
    anelli
    0.43
    olino
    0.40
    Portail
    0.40
    elli
    0.40
    etti
    0.38
    ciano
    0.37
    co
    0.36
    monių
    0.36
    ino
    0.36
    arini
    0.36
    Activations Density 1.278%

    No Known Activations