© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 249048
    Prev
    Next
    INDEX
    Explanations

    up

    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_56_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
    John
    0.46
     growing
    0.44
    year
    0.43
     wanting
    0.42
    years
    0.42
     watching
    0.40
     John
    0.40
     低
    0.38
    ச
    0.38
    を聞
    0.38
    POSITIVE LOGITS
     SINGLE
    0.59
     single
    0.56
    Single
    0.54
     Single
    0.54
     सिंगल
    0.53
     Raising
    0.50
     raising
    0.50
     raise
    0.48
     identificado
    0.48
    single
    0.47
    Activations Density 0.000%

    No Known Activations