© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53250
    Prev
    Next
    INDEX
    Explanations

    immediately or right after

    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_30_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
     Spiel
    0.37
    🍒
    0.36
    ליה
    0.35
    rainte
    0.34
    രിച്ചി
    0.34
    ፈል
    0.32
    вах
    0.32
     ওভার
    0.32
    XH
    0.32
     動
    0.32
    POSITIVE LOGITS
     immediately
    1.26
     сразу
    1.14
    immediately
    1.13
     odmah
    1.08
     Immediately
    1.06
    Immediately
    1.05
     imediat
    0.99
     imediatamente
    0.98
    立即
    0.96
    立刻
    0.95
    Activations Density 0.057%

    No Known Activations