© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17410
    Prev
    Next
    INDEX
    Explanations

    hypertext transfer protocol

    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_34_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
    elow
    0.42
    where
    0.38
    joy
    0.37
     Pleasure
    0.36
    aceut
    0.36
     revi
    0.36
    扁
    0.35
    enjoy
    0.35
     Scottsdale
    0.34
    acknowledge
    0.34
    POSITIVE LOGITS
     hyper
    0.46
     作
    0.41
     poppy
    0.39
     छू
    0.39
     crisis
    0.39
     PROBLEMS
    0.39
     hiper
    0.38
     verses
    0.38
    umas
    0.37
    发展
    0.37
    Activations Density 0.042%

    No Known Activations