© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 176584
    Prev
    Next
    INDEX
    Explanations

    Chewbacca

    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
    시키
    0.38
     khe
    0.38
    簌
    0.38
    éral
    0.37
    assays
    0.36
    нтип
    0.36
    elsk
    0.36
     صفحۀ
    0.36
     لاب
    0.36
    ADIAN
    0.35
    POSITIVE LOGITS
    Av
    0.43
    Murray
    0.39
    Approved
    0.38
    Eo
    0.38
    rea
    0.37
     Ave
    0.37
     Murray
    0.37
     m
    0.37
    lores
    0.37
     greatly
    0.36
    Activations Density 0.000%

    No Known Activations