© 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. 169658
    Prev
    Next
    INDEX
    Explanations

    Mason

    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
    上看
    0.40
    aní
    0.40
     ASSEM
    0.40
    bate
    0.38
    טח
    0.37
    磡
    0.37
     Sovi
    0.37
     ម
    0.36
     Polda
    0.36
    本格
    0.35
    POSITIVE LOGITS
    ry
    0.78
    Ry
    0.75
     ry
    0.74
    ery
    0.72
    RY
    0.72
     Ry
    0.71
    ary
    0.68
    ERY
    0.64
    ory
    0.63
     Ryder
    0.60
    Activations Density 0.000%

    No Known Activations