© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36396
    Prev
    Next
    INDEX
    Explanations

    New area, new energy, new deal

    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_11_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
    この
    0.39
    (
    0.37
    л
    0.36
    I
    0.36
     of
    0.35
     Annual
    0.31
    ;
    0.31
                    
    0.30
    With
    0.30
    Its
    0.30
    POSITIVE LOGITS
    ாஹ
    0.35
    ₸
    0.34
    alakip
    0.34
    𝙡
    0.34
    𝒹
    0.33
    𝙜
    0.32
    wapV
    0.32
     fuss
    0.31
    δη
    0.31
    cipit
    0.30
    Activations Density 0.006%

    No Known Activations