© 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. 14808
    Prev
    Next
    INDEX
    Explanations

    mentions of trails and years.

    oai_token-act-pair · gemini-2.0-flash

    temporal references

    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
     hjer
    -0.56
     kropp
    -0.54
     bevis
    -0.53
     waarde
    -0.51
    Française
    -0.51
     hjär
    -0.51
     Eisenberg
    -0.51
     uș
    -0.51
    SourceChecksum
    -0.49
     grecque
    -0.49
    POSITIVE LOGITS
     Houſe
    0.79
     Efq
    0.79
     myſelf
    0.76
     houſe
    0.75
     Monfieur
    0.74
     Jefus
    0.73
    Билгалдахарш
    0.73
     Theſe
    0.71
     Reſ
    0.70
     purpoſe
    0.70
    Activations Density 11.728%

    No Known Activations