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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 204590
    Prev
    Next
    INDEX
    Explanations

    #include directives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
     ورک
    0.35
    Rx
    0.32
    Ｑ
    0.32
    제
    0.31
     honoured
    0.31
    𝘾
    0.31
     retract
    0.30
    走进
    0.30
     পরিস্কার
    0.30
     দুর্ভোগ
    0.30
    POSITIVE LOGITS
    reportBody
    0.41
    フォード
    0.40
     помощь
    0.39
    नीत
    0.38
    𒊑
    0.38
     तत्वा
    0.37
     عض
    0.37
     vorhand
    0.36
     colocando
    0.36
     प्रमाण
    0.36
    Activations Density 0.001%

    No Known Activations