© 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. 141067
    Prev
    Next
    INDEX
    Explanations

    know what you're doing

    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
    Ⴝ
    0.58
    Logs
    0.54
    ATIVE
    0.53
    ajt
    0.51
    égation
    0.49
    捚
    0.49
    JobList
    0.49
    ITIES
    0.49
    SNR
    0.49
    WordPress
    0.49
    POSITIVE LOGITS
    ٥
    0.58
    qu
    0.51
    agamo
    0.51
    aka
    0.50
     miserable
    0.50
    ↵
    0.50
    ك
    0.48
    ٣
    0.48
     an
    0.47
    ely
    0.47
    Activations Density 0.000%

    No Known Activations