© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 42766
    Prev
    Next
    INDEX
    Explanations

    pool descriptions and features

    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_13_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
    कू
    0.57
    irect
    0.50
    וי
    0.49
    ץ
    0.49
    선
    0.48
    ن
    0.48
    ፈል
    0.48
    mil
    0.48
    :,
    0.47
     efectivos
    0.47
    POSITIVE LOGITS
     এইভাবে
    0.48
    ্ড
    0.46
     Figura
    0.46
     Worte
    0.45
     terroir
    0.45
    áról
    0.44
    FERENCE
    0.43
     Farbe
    0.43
     ^{\
    0.43
    sofar
    0.42
    Activations Density 0.000%

    No Known Activations