© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166086
    Prev
    Next
    INDEX
    Explanations

    model predictive control

    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_31_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
     mantras
    0.33
     হেসে
    0.33
    透
    0.32
    เสียง
    0.31
    ঝে
    0.31
    傾向
    0.31
    Ϝ
    0.31
    )}-
    0.31
    robots
    0.31
     取っ
    0.31
    POSITIVE LOGITS
     ficaram
    0.37
     компенса
    0.36
     did
    0.36
     Compensation
    0.33
     teste
    0.33
    retti
    0.32
     didn
    0.32
     moment
    0.31
    omyces
    0.31
     Brawl
    0.31
    Activations Density 0.005%

    No Known Activations