© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3286
    Prev
    Next
    INDEX
    Explanations

    speech transcription and presentation structure

    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_5_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
    ST
    1.08
    िक
    0.98
    퀴
    0.97
    ين
    0.96
    Airline
    0.96
    en
    0.95
    e
    0.91
    snapshot
    0.91
    Julian
    0.89
     небо
    0.87
    POSITIVE LOGITS
     trusses
    1.17
    pośred
    1.13
    డు
    1.13
    យៈ
    1.11
    ামুটি
    1.10
    "]
    1.09
     ducts
    1.07
     pitfalls
    1.07
     thậm
    1.07
    "},
    1.06
    Activations Density 0.002%

    No Known Activations