© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28992
    Prev
    Next
    INDEX
    Explanations

    following rules and guidelines

    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_10_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
     przesz
    0.48
     était
    0.47
     gł
    0.46
     oznacza
    0.46
     questa
    0.46
     około
    0.46
     з
    0.45
     była
    0.45
     markets
    0.45
     inizia
    0.45
    POSITIVE LOGITS
    (
    0.39
    MR
    0.36
    EM
    0.35
    Compliance
    0.35
    icken
    0.35
    amil
    0.34
    EST
    0.34
    ENO
    0.33
    Feb
    0.33
    Emple
    0.33
    Activations Density 0.163%

    No Known Activations