© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9196
    Prev
    Next
    INDEX
    Explanations

    miscellaneous technical content

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    )}/>
    0.74
    illary
    0.64
     Abo
    0.63
    genheim
    0.63
     Licensing
    0.63
    Turbo
    0.63
    러스
    0.62
     Gesundheit
    0.62
    loan
    0.62
    Addo
    0.62
    POSITIVE LOGITS
    肘
    0.66
    结点
    0.63
     ܥ
    0.62
     neglig
    0.59
     বিশ্বের
    0.59
     égales
    0.59
    oxymethyl
    0.57
    粪
    0.57
     kyun
    0.57
     Klav
    0.57
    Activations Density 0.090%

    No Known Activations