© 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. 5123
    Prev
    Next
    INDEX
    Explanations

    language translation

    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
    as
    3.29
    कर्ता
    2.70
     overwhelming
    2.66
    entreprise
    2.60
    ^{+}$
    2.59
    ्ट
    2.48
    ग्रस्त
    2.46
    াপ
    2.45
    ers
    2.44
    voor
    2.43
    POSITIVE LOGITS
    м
    3.53
    󠁮
    3.08
    woman
    3.04
    Speaking
    2.85
    speaking
    2.82
    ش
    2.77
    n
    2.75
    ल
    2.72
    seas
    2.66
    BadRequest
    2.57
    Activations Density 0.045%

    No Known Activations