© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 123322
    Prev
    Next
    INDEX
    Explanations

    revolving door, conf, credit facilities

    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_3_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
     приве
    0.86
    рного
    0.67
    ه
    0.65
    cannot
    0.65
    وكان
    0.65
    ﺍ
    0.64
    اولة
    0.63
    t
    0.63
    h
    0.63
     апре
    0.62
    POSITIVE LOGITS
    هم
    0.82
     to
    0.81
     on
    0.78
    দের
    0.76
    อง
    0.72
     an
    0.71
     energy
    0.68
    يل
    0.66
    ern
    0.65
     Solving
    0.65
    Activations Density 0.000%

    No Known Activations