© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 129820
    Prev
    Next
    INDEX
    Explanations

    going viral

    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_6_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
    ates
    1.41
    v
    1.25
    ett
    1.16
    ated
    1.15
    ard
    1.14
    em
    1.11
    I
    1.11
    im
    1.09
    th
    1.09
    atic
    1.04
    POSITIVE LOGITS
     ferramenta
    1.04
     raiz
    0.99
     dupla
    0.98
     prevista
    0.95
     temprana
    0.94
     raíz
    0.90
     ferramentas
    0.90
     espí
    0.89
     irá
    0.89
    ерез
    0.88
    Activations Density 0.001%

    No Known Activations