© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 149873
    Prev
    Next
    INDEX
    Explanations

    LI

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    Ta
    0.53
    O
    0.52
    Ti
    0.51
    Tor
    0.47
    та
    0.46
    Ai
    0.45
    𝙨
    0.44
    Ag
    0.44
    Term
    0.44
    Sy
    0.44
    POSITIVE LOGITS
    گون
    0.48
    ife
    0.46
     Dov
    0.44
     Dove
    0.43
    dove
    0.42
    ASER
    0.40
    eep
    0.40
    APE
    0.40
     grate
    0.40
     dode
    0.40
    Activations Density 0.000%

    No Known Activations