© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38675
    Prev
    Next
    INDEX
    Explanations

    starship

    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_3_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
    ’
    0.85
    ات
    0.77
    ין
    0.75
    ت
    0.75
    ี
    0.75
    י
    0.74
    ين
    0.69
    ي
    0.68
    ה
    0.67
    it
    0.66
    POSITIVE LOGITS
    closes
    0.69
    ferm
    0.64
     ಸ್ವಲ್ಪ
    0.61
    thickmathspace
    0.60
     मोठ्या
    0.59
     Германия
    0.59
    kl
    0.58
    pg
    0.58
    managed
    0.57
    fonts
    0.57
    Activations Density 0.012%

    No Known Activations