© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 92490
    Prev
    Next
    INDEX
    Explanations

    Voc

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     Behold
    0.45
    backer
    0.45
    minent
    0.43
    minimize
    0.43
    monotonic
    0.43
    mut
    0.41
    )^{[\
    0.41
    buie
    0.40
    compens
    0.40
     Them
    0.40
    POSITIVE LOGITS
     of
    0.47
    t
    0.46
    ty
    0.46
    tc
    0.45
    ib
    0.45
    ივ
    0.44
     TS
    0.44
     bt
    0.43
     dd
    0.43
    ts
    0.42
    Activations Density 0.000%

    No Known Activations