© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 215099
    Prev
    Next
    INDEX
    Explanations

    strong

    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_5_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
    to
    1.60
    L
    1.31
    EN
    1.27
    B
    1.24
    Bottle
    1.22
    BAC
    1.22
    AL
    1.21
    ಮ
    1.20
    ام
    1.20
    DRIVER
    1.19
    POSITIVE LOGITS
     verific
    1.31
    a
    1.30
    ה
    1.26
     divulg
    1.18
     majeure
    1.18
    t
    1.18
    त
    1.16
    .
    1.14
     configur
    1.10
     prescriptive
    1.10
    Activations Density 0.000%

    No Known Activations