© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 102882
    Prev
    Next
    INDEX
    Explanations

    material properties

    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_44_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
     Pillow
    0.53
     pillow
    0.52
    pillow
    0.44
     കാ
    0.41
    亲
    0.41
    pkt
    0.40
    关系
    0.39
    ʬ
    0.38
    Pocket
    0.38
     blessing
    0.37
    POSITIVE LOGITS
     matur
    0.41
    िडिओ
    0.40
     spirals
    0.39
    chart
    0.38
    touch
    0.38
     artic
    0.38
    靱
    0.37
     pesantren
    0.37
     endregion
    0.36
     mature
    0.36
    Activations Density 0.033%

    No Known Activations