© 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. 61203
    Prev
    Next
    INDEX
    Explanations

    letters after J

    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
     (
    1.38
     was
    1.33
     oxid
    1.10
     you
    1.07
     synthes
    1.02
    on
    1.00
    s
    0.98
     as
    0.93
    S
    0.87
    的多
    0.87
    POSITIVE LOGITS
    ي
    1.66
    ت
    1.38
    ி
    1.38
    t
    1.35
    т
    1.25
    י
    1.19
    д
    1.12
    рт
    1.10
    يّ
    1.08
    ಾ
    1.06
    Activations Density 0.000%

    No Known Activations