© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44836
    Prev
    Next
    INDEX
    Explanations

    Cross-Site Request Forgery (CSRF)

    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_22_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
    דול
    0.45
    }}\|
    0.44
    May
    0.41
     параметра
    0.41
    氲
    0.41
    ⿶
    0.41
    নাম
    0.40
     sixth
    0.40
     distinctive
    0.39
     স্মৃতি
    0.39
    POSITIVE LOGITS
    ковского
    0.42
    ingham
    0.42
    രിക്കും
    0.41
    institute
    0.41
    urna
    0.39
    ணிய
    0.39
    骢
    0.39
     conquer
    0.39
     conquering
    0.38
    вим
    0.38
    Activations Density 0.001%

    No Known Activations