© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101033
    Prev
    Next
    INDEX
    Explanations

    combat, inoculation, running

    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_14_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
     sobre
    0.49
     Elena
    0.49
    hexa
    0.48
    elola
    0.47
    Aslamualaikum
    0.47
     vadama
    0.46
    碚
    0.46
    劶
    0.46
     Казіно
    0.46
     Extern
    0.46
    POSITIVE LOGITS
    uye
    0.53
    C
    0.49
    c
    0.49
    '
    0.48
     machines
    0.48
    Cutting
    0.47
    ค
    0.45
     compression
    0.45
    sey
    0.44
     C
    0.44
    Activations Density 0.010%

    No Known Activations