© 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. 132461
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    antwoord
    0.37
    resti
    0.36
    barang
    0.35
    <i>
    0.35
    ύ
    0.33
    hit
    0.33
    ъ
    0.33
    区
    0.33
     되었
    0.33
    धित
    0.32
    POSITIVE LOGITS
     সঙ্গ
    0.41
    WORKS
    0.38
    >)`](
    0.37
     referrerpolicy
    0.37
    copic
    0.36
    ;%%
    0.36
     않아
    0.35
    𝗸
    0.35
    োয়
    0.35
    گنڈ
    0.34
    Activations Density 0.178%

    No Known Activations