© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 195255
    Prev
    Next
    INDEX
    Explanations

    showing initiative

    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_15_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
    LR
    0.56
    Fire
    0.54
    CA
    0.51
    ྥ
    0.51
    FM
    0.50
    2
    0.49
    CM
    0.48
    FIRE
    0.48
    જી
    0.47
    sim
    0.46
    POSITIVE LOGITS
     müs
    0.59
     concepto
    0.56
     når
    0.54
     território
    0.54
     τὸ
    0.54
     Patienten
    0.53
     Ellie
    0.53
     bệnh
    0.52
     ornith
    0.52
     ન
    0.52
    Activations Density 0.002%

    No Known Activations