© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 259283
    Prev
    Next
    INDEX
    Explanations

    complexconstructor

    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_22_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
     hanno
    0.47
    urate
    0.46
     solche
    0.46
     detta
    0.44
    ijing
    0.44
    ate
    0.43
     r
    0.43
     wy
    0.43
    是不
    0.43
     mujer
    0.42
    POSITIVE LOGITS
    ssystem
    0.48
    冷凍
    0.46
     Иң
    0.46
    stove
    0.45
     setMessage
    0.44
    sendMessage
    0.44
    orben
    0.44
    .-(
    0.43
    machines
    0.43
    reqParams
    0.42
    Activations Density 0.000%

    No Known Activations