© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 76842
    Prev
    Next
    INDEX
    Explanations

    input functions

    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_31_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
     tarif
    0.28
     راہ
    0.27
     föret
    0.26
    राइड
    0.26
    ڈ
    0.25
    ولندا
    0.25
    axy
    0.25
     Troy
    0.24
     лидер
    0.24
     പു
    0.24
    POSITIVE LOGITS
     後
    0.26
    的核心
    0.24
     overkill
    0.23
     intensity
    0.23
    部
    0.23
    💊
    0.22
     return
    0.22
     Intensity
    0.22
    苗
    0.22
    :(
    0.22
    Activations Density 0.000%

    No Known Activations