© 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. 45517
    Prev
    Next
    INDEX
    Explanations

    Q code or query code

    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
    त्रि
    0.72
    ಕ
    0.71
    کسی
    0.70
    کار
    0.69
     nostru
    0.68
    ओं
    0.68
    ли
    0.66
    若い
    0.66
     veineux
    0.66
    은
    0.66
    POSITIVE LOGITS
    at
    0.76
    ao
    0.72
    O
    0.68
    P
    0.67
    TST
    0.66
    H
    0.64
    ats
    0.60
    orak
    0.59
    amn
    0.59
    ally
    0.57
    Activations Density 0.005%

    No Known Activations