© 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. 12097
    Prev
    Next
    INDEX
    Explanations

    fragments of conversation and code and quoted texts

    oai_token-act-pair · gemini-2.0-flash

    apostrophe

    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
    ^(@)
    -1.02
     Efq
    -1.01
     myſelf
    -1.00
     Theſe
    -0.93
     Monfieur
    -0.90
     Houſe
    -0.86
     itſelf
    -0.86
     Jefus
    -0.86
     himſelf
    -0.82
     themſelves
    -0.80
    POSITIVE LOGITS
    ll
    1.09
    re
    1.09
    ve
    1.00
    d
    0.98
    m
    0.97
    nt
    0.88
    s
    0.88
    n
    0.79
    ts
    0.79
    4
    0.78
    Activations Density 15.901%

    No Known Activations