© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207969
    Prev
    Next
    INDEX
    Explanations

    major [noun]

    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_20_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
    ologio
    0.32
    ково
    0.30
    鱼
    0.29
     ఊ
    0.28
    `),
    0.27
    ateľ
    0.26
     点击
    0.26
    Voilà
    0.26
     verlieren
    0.26
    šķ
    0.25
    POSITIVE LOGITS
     crates
    0.33
    者に
    0.31
    पहरण
    0.31
     *\
    0.30
    補助
    0.30
     creates
    0.29
    𝙼
    0.29
     ايجاد
    0.29
     crear
    0.29
     Carthage
    0.29
    Activations Density 0.007%

    No Known Activations