© 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. 170188
    Prev
    Next
    INDEX
    Explanations

    say r

    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
     R
    0.50
     Ri
    0.50
     Ra
    0.43
     Ram
    0.41
     Rh
    0.40
     RI
    0.40
    ọt
    0.39
     Rac
    0.39
     Ritz
    0.39
    MiddleLine
    0.37
    POSITIVE LOGITS
    rs
    0.61
    chr
    0.60
    vr
    0.59
    ｒ
    0.59
    стр
    0.58
    schr
    0.58
    zr
    0.57
     CBR
    0.56
     GSR
    0.55
    nr
    0.55
    Activations Density 0.000%

    No Known Activations