© 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. 209218
    Prev
    Next
    INDEX
    Explanations

    public function/static/event declarations

    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
    십시오
    0.40
    šť
    0.38
    یکیشن
    0.38
    🅽
    0.38
    “
    0.38
     праздник
    0.36
    뺐
    0.36
    )_{\
    0.36
    玺
    0.36
    udeau
    0.36
    POSITIVE LOGITS
    Arrows
    0.37
     principaux
    0.36
     Dots
    0.36
    (
    0.36
    ingen
    0.34
     Pieces
    0.34
    髙
    0.34
    ，
    0.34
     type
    0.33
    ារ
    0.33
    Activations Density 0.000%

    No Known Activations