© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23801
    Prev
    Next
    INDEX
    Explanations

    US states

    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_56_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
     Ma
    0.44
     ma
    0.40
    Ma
    0.40
    ka
    0.38
     Il
    0.38
     Ca
    0.38
    ß
    0.38
    Ca
    0.38
    robots
    0.38
     il
    0.37
    POSITIVE LOGITS
     Gef
    1.71
     gef
    1.38
    gef
    1.31
     GF
    0.85
     gf
    0.73
    GF
    0.66
     gfx
    0.60
     GFP
    0.56
    gf
    0.54
    gfx
    0.48
    Activations Density 0.004%

    No Known Activations