© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 46349
    Prev
    Next
    INDEX
    Explanations

    white crystals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    st
    0.76
    ul
    0.73
    вя
    0.65
    ა
    0.64
    ka
    0.61
    ect
    0.60
    á
    0.59
    ى
    0.59
    ver
    0.58
    𝐧
    0.58
    POSITIVE LOGITS
    لی
    0.79
     to
    0.75
    کن
    0.71
     ی
    0.69
    اک
    0.68
     ニ
    0.67
     inclement
    0.65
     می‌کند
    0.64
    లు
    0.63
    یکی
    0.63
    Activations Density 0.003%

    No Known Activations