© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9251
    Prev
    Next
    INDEX
    Explanations

    service discovery

    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
     flashing
    0.52
     herz
    0.52
     bikers
    0.50
     contando
    0.50
     fillings
    0.49
     enorme
    0.48
     harapan
    0.48
    **,
    0.48
     bastante
    0.47
     repent
    0.47
    POSITIVE LOGITS
    unes
    0.54
    ضو
    0.48
    NEUTRON
    0.48
    CLE
    0.46
    چل
    0.45
    ку
    0.45
    jeux
    0.45
    湫
    0.44
    TIME
    0.44
    Remove
    0.44
    Activations Density 0.034%

    No Known Activations