© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42349
    Prev
    Next
    INDEX
    Explanations

    ask for information or help

    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_13_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
    i
    0.75
    f
    0.70
    ي
    0.57
     prompts
    0.55
     rehearsals
    0.54
    h
    0.54
     analogs
    0.53
     celebs
    0.52
    ி
    0.52
    ﯼ
    0.51
    POSITIVE LOGITS
    /
    0.54
    、
    0.51
    –
    0.50
    瓦
    0.48
     तालुक
    0.46
     Израи
    0.46
    vas
    0.45
    ulation
    0.45
    λάβ
    0.45
     Lore
    0.43
    Activations Density 0.060%

    No Known Activations