© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 158508
    Prev
    Next
    INDEX
    Explanations

    path

    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_50_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
     Gustaf
    0.41
     मुद्दों
    0.40
     архів
    0.39
     rentrer
    0.39
     궁
    0.38
     புரா
    0.38
     soov
    0.36
     Lovers
    0.36
     Kla
    0.36
     .^{
    0.36
    POSITIVE LOGITS
     intellectual
    0.40
    czną
    0.38
    Given
    0.38
     given
    0.37
     പിന്നീട്
    0.36
    qed
    0.36
    確実に
    0.36
     Intellectual
    0.35
    llo
    0.35
    gic
    0.35
    Activations Density 0.004%

    No Known Activations