© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 122274
    Prev
    Next
    INDEX
    Explanations

    square root calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_37_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
    hb
    0.38
    vat
    0.37
    痧
    0.37
    igia
    0.36
    luit
    0.35
     MATRIX
    0.35
    vodu
    0.35
    urgie
    0.35
    hava
    0.35
    byter
    0.35
    POSITIVE LOGITS
     extremely
    0.49
     estremamente
    0.47
    万
    0.46
    extremely
    0.45
     extremamente
    0.45
     million
    0.44
     Extremely
    0.43
     extremadamente
    0.43
     milion
    0.41
     exceedingly
    0.40
    Activations Density 0.005%

    No Known Activations