© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59177
    Prev
    Next
    INDEX
    Explanations

    luchtluftluster

    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
    c
    1.55
     It
    1.46
    v
    1.41
    ت
    1.40
     I
    1.35
    f
    1.25
    ات
    1.22
     on
    1.19
    k
    1.19
    d
    1.18
    POSITIVE LOGITS
    та
    1.30
    ↵↵
    1.08
    ing
    1.08
    5
    1.06
    是
    1.06
    Só
    1.05
     և
    1.02
    0.97
    Pentru
    0.97
    τή
    0.96
    Activations Density 0.003%

    No Known Activations