© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 141974
    Prev
    Next
    INDEX
    Explanations

    magnetic field lines

    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_12_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
    O
    0.53
    Magnet
    0.50
    electrical
    0.50
    Electrical
    0.49
    c
    0.49
     electricians
    0.48
    Shapes
    0.48
    OA
    0.47
    super
    0.47
    role
    0.47
    POSITIVE LOGITS
     Расійскай
    0.59
    化
    0.59
     化
    0.59
     inactivation
    0.59
     വിവര
    0.59
     glycemic
    0.55
     phenotypic
    0.55
     Bowman
    0.55
     mois
    0.55
     multin
    0.55
    Activations Density 0.001%

    No Known Activations