© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 91350
    Prev
    Next
    INDEX
    Explanations

    amb

    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
    ي
    0.49
    i
    0.46
    ी
    0.42
    ič
    0.41
    ೨
    0.41
    r
    0.40
    ваться
    0.39
    ૨
    0.38
    <0x91>
    0.38
     gegründet
    0.37
    POSITIVE LOGITS
     NOS
    0.49
     PGS
    0.48
     AOS
    0.48
     ESO
    0.45
     DSO
    0.45
     POR
    0.44
     ERIC
    0.44
     PRS
    0.43
     Muni
    0.43
     EOS
    0.42
    Activations Density 0.000%

    No Known Activations