© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 199036
    Prev
    Next
    INDEX
    Explanations

    bending, broken, ending

    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_15_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
     clé
    0.53
     effectu
    0.53
     Isso
    0.52
     andere
    0.51
     outras
    0.51
     thine
    0.51
    ť
    0.50
     müsste
    0.50
     más
    0.49
     donc
    0.49
    POSITIVE LOGITS
    >∕
    0.55
    azionale
    0.52
    RUNTIME
    0.50
    skom
    0.49
    ֆ
    0.49
    CEEDINGS
    0.49
    obarbital
    0.48
    libc
    0.47
    ICPSR
    0.47
    ográf
    0.47
    Activations Density 0.000%

    No Known Activations