© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48810
    Prev
    Next
    INDEX
    Explanations

    ke

    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_55_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
    Bir
    0.44
     конца
    0.39
     Johannes
    0.39
     Birk
    0.39
    wells
    0.38
    bir
    0.37
    冈
    0.37
     revol
    0.37
     Verlet
    0.36
    (--
    0.36
    POSITIVE LOGITS
    ys
    0.42
    ｙ
    0.41
    pt
    0.41
    zzle
    0.39
    ्यादा
    0.39
    yscale
    0.38
    ethy
    0.38
    istert
    0.38
    le
    0.38
     সাহায্যের
    0.37
    Activations Density 0.001%

    No Known Activations