© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 7217
    Prev
    Next
    INDEX
    Explanations

    html/css titles

    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_40_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
     womb
    0.19
     barely
    0.19
    kate
    0.18
     invincible
    0.18
    πού
    0.18
     mystical
    0.18
    :"))
    0.18
     Busch
    0.17
    rugged
    0.17
     explorers
    0.17
    POSITIVE LOGITS
     содержания
    0.18
     Solidarity
    0.18
    žit
    0.18
    ၃
    0.17
    ﾒ
    0.17
     //{
    0.17
    '].'
    0.17
    <0xBB>
    0.17
     drawSprites
    0.17
    ತು
    0.16
    Activations Density 0.000%

    No Known Activations