© 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. 89848
    Prev
    Next
    INDEX
    Explanations

    medium heat

    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
    of
    0.26
    rne
    0.23
    rn
    0.23
    ות
    0.22
    0.22
    怿
    0.22
    ++;
    0.21
    {
    0.21
    r
    0.21
    rı
    0.21
    POSITIVE LOGITS
    kHz
    0.21
    敞
    0.21
    ussie
    0.20
     høy
    0.20
    ली
    0.20
    ulan
    0.20
    itekt
    0.20
     shimmering
    0.20
    akili
    0.20
    uksia
    0.19
    Activations Density 0.021%

    No Known Activations