© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5163
    Prev
    Next
    INDEX
    Explanations

    introduction to a response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disb
    0.89
     glad
    0.86
    ۸
    0.85
     Adm
    0.82
     foregoing
    0.82
    excluding
    0.81
    िश
    0.80
    ଉ
    0.80
     Среди
    0.79
    ଟ
    0.78
    POSITIVE LOGITS
    THING
    1.35
    д
    1.26
    dür
    1.12
    й
    1.10
    <bos>
    1.09
    iin
    1.02
    ल
    1.02
    ం
    1.00
    ی
    1.00
    ää
    0.98
    Activations Density 0.147%

    No Known Activations