© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138677
    Prev
    Next
    INDEX
    Explanations

    deductive reasoning

    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
    ud
    0.67
     Glut
    0.57
    E
    0.57
    abal
    0.57
    rd
    0.56
    funds
    0.56
    ust
    0.55
    I
    0.55
    thy
    0.55
    urm
    0.55
    POSITIVE LOGITS
     tarix
    0.52
     esempl
    0.51
    ят
    0.50
    閆
    0.49
     pretext
    0.49
     ließ
    0.48
     дописа
    0.47
    地
    0.47
    ूट
    0.46
     ráp
    0.46
    Activations Density 0.001%

    No Known Activations