© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31091
    Prev
    Next
    INDEX
    Explanations

    community and 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_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
     গভ
    0.44
     uczni
    0.41
    beiten
    0.38
     Zav
    0.38
     Calyce
    0.38
    пас
    0.38
    朊
    0.38
    邑
    0.38
     Kult
    0.37
    ޓ
    0.37
    POSITIVE LOGITS
    ROUTES
    0.38
     oxides
    0.37
    Chand
    0.37
     PM
    0.35
    asem
    0.35
    route
    0.35
    arro
    0.35
    oxides
    0.35
    Routine
    0.35
    CEA
    0.34
    Activations Density 0.007%

    No Known Activations