© 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. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3331
    Prev
    Next
    INDEX
    Explanations

    time references, especially relative ones like "last" or "this"

    oai_token-act-pair · gemini-2.0-flash

    Time periods

    np_max-act-logits · 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
    chiato
    -0.59
     endwhile
    -0.54
    heet
    -0.54
     MOA
    -0.54
     GOB
    -0.53
    piram
    -0.53
     Paglinawan
    -0.52
     Kees
    -0.52
    heets
    -0.52
    eef
    -0.51
    POSITIVE LOGITS
    LookAnd
    0.68
    Przypisy
    0.54
    FTFY
    0.52
    TabIndex
    0.51
    Rè
    0.50
    Sprintf
    0.50
    igshid
    0.49
    Contribute
    0.49
    XMLSchema
    0.48
     وتسجيلات
    0.48
    Activations Density 1.546%

    No Known Activations