© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133222
    Prev
    Next
    INDEX
    Explanations

    mockups

    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_1_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
    n
    1.09
    el
    1.05
     as
    1.04
    我们
    0.98
    \
    0.98
     hydrocarbons
    0.97
    -
    0.96
     incisions
    0.94
    :
    0.94
     y
    0.93
    POSITIVE LOGITS
    it
    1.27
    ח
    1.24
     Mungkin
    1.13
    도
    1.13
    も
    1.12
    ح
    1.10
    ਣ
    1.10
    마
    1.09
    ید
    1.08
    니다
    1.06
    Activations Density 0.001%

    No Known Activations