© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101600
    Prev
    Next
    INDEX
    Explanations

    yearly compounding

    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_16_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
    ani
    0.53
    anch
    0.52
     i
    0.50
    ati
    0.50
     and
    0.49
    ank
    0.45
    asp
    0.45
    ads
    0.44
    avi
    0.44
    adani
    0.44
    POSITIVE LOGITS
    茈
    0.65
    ുകെ
    0.51
    निश्ड
    0.49
    대학
    0.49
    イルド
    0.48
    ებლ
    0.47
    此同时
    0.47
    속
    0.47
    İZ
    0.46
     бір
    0.46
    Activations Density 0.000%

    No Known Activations