© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32304
    Prev
    Next
    INDEX
    Explanations

    rotary

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Rott
    0.44
     टर्म
    0.42
     conditioning
    0.41
    ミ
    0.40
    Rot
    0.39
    垁
    0.38
     बी
    0.38
     Conditioning
    0.38
    미
    0.38
     Rot
    0.38
    POSITIVE LOGITS
    isser
    0.51
    ivesse
    0.49
    Hash
    0.44
    Fred
    0.41
    obod
    0.41
     TSS
    0.41
    Mas
    0.40
    देशीर
    0.40
    bug
    0.39
     viss
    0.39
    Activations Density 0.001%

    No Known Activations