© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 101270
    Prev
    Next
    INDEX
    Explanations

    export const/function

    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_14_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
     bepaalde
    0.57
     handlers
    0.52
    轅
    0.52
     mnemonic
    0.50
     gesturing
    0.50
     droid
    0.50
     recyclable
    0.50
    ת
    0.49
    ጐ
    0.49
     leather
    0.49
    POSITIVE LOGITS
    j
    0.86
    q
    0.71
    प
    0.68
    f
    0.67
    ja
    0.64
    m
    0.64
    z
    0.63
    pp
    0.63
    sa
    0.62
     إ
    0.62
    Activations Density 0.000%

    No Known Activations