© 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. 42103
    Prev
    Next
    INDEX
    Explanations

    BOT

    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
    ুল
    0.70
    t
    0.70
    ه
    0.70
    𝙪
    0.66
    anneer
    0.63
    𝙏
    0.63
    iné
    0.63
     not
    0.63
    ट
    0.63
    𝘾
    0.63
    POSITIVE LOGITS
    I
    0.93
    며
    0.70
    โดย
    0.60
    вого
    0.59
    ొప్పి
    0.58
    νει
    0.58
    बद्ध
    0.57
    ..,
    0.57
    '(
    0.57
     توسط
    0.56
    Activations Density 0.001%

    No Known Activations