© 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. 214407
    Prev
    Next
    INDEX
    Explanations

    Elektro

    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
     CH
    0.41
     Bers
    0.40
     Holton
    0.40
     Alli
    0.40
     دوب
    0.39
     terp
    0.39
     ഖ
    0.39
     ber
    0.39
     EXP
    0.39
     Spr
    0.39
    POSITIVE LOGITS
    hi
    0.43
    ᴺ
    0.39
     hi
    0.39
    히
    0.39
    гө
    0.37
    oplankton
    0.36
     সভ
    0.36
     প্রোগ্রাম
    0.36
    ﾋ
    0.36
    бил
    0.36
    Activations Density 0.001%

    No Known Activations