© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89104
    Prev
    Next
    INDEX
    Explanations

    focus energy on

    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_23_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
     desist
    0.35
     vulnerability
    0.35
     جنوب
    0.34
     commandment
    0.34
    芷
    0.34
     deserial
    0.33
     spline
    0.33
     redeem
    0.33
     rembour
    0.33
    GameOver
    0.33
    POSITIVE LOGITS
    했는데
    0.43
    know
    0.40
     Estado
    0.40
    known
    0.38
     Place
    0.37
     Puedes
    0.37
    Ь
    0.36
    gten
    0.36
     לכ
    0.36
    effetto
    0.35
    Activations Density 0.016%

    No Known Activations