© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159090
    Prev
    Next
    INDEX
    Explanations

    chipping, chirp, chu, chili

    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_2_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
    л
    1.36
    speople
    1.34
    ל
    1.20
     effusion
    1.15
    زیز
    1.15
     ailments
    1.10
     axles
    1.10
    ts
    1.09
     самим
    1.09
     اختی
    1.09
    POSITIVE LOGITS
    は
    1.84
    是
    1.82
     not
    1.55
    1.53
    ৬
    1.53
    >
    1.48
    أ
    1.48
     de
    1.46
    ية
    1.44
    The
    1.41
    Activations Density 0.000%

    No Known Activations