© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261442
    Prev
    Next
    INDEX
    Explanations

    collect all items

    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_22_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
     femelle
    0.15
    ホル
    0.15
    NSA
    0.15
    ilane
    0.14
     mate
    0.14
     tensors
    0.14
    lorescence
    0.14
    <0xBE>
    0.13
    ்கு
    0.13
    しさ
    0.13
    POSITIVE LOGITS
     Progress
    0.17
     Atual
    0.17
     Hiện
    0.16
     fogl
    0.16
     παρου
    0.16
     html
    0.15
    रिपोर्ट
    0.15
    获得
    0.15
     क्रिप्ट
    0.15
     gaming
    0.15
    Activations Density 0.008%

    No Known Activations