© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121721
    Prev
    Next
    INDEX
    Explanations

    .cornerRadius / .padding

    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_37_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
    "]).
    0.42
     হস্তে
    0.39
    zięki
    0.38
    酗
    0.37
    textColor
    0.37
    Frederick
    0.37
     jLabel
    0.36
    ంత
    0.36
    㭂
    0.36
    రువు
    0.36
    POSITIVE LOGITS
     MIG
    0.44
     Messer
    0.42
     Mig
    0.40
     paste
    0.39
    Mig
    0.39
     Pag
    0.38
    paste
    0.38
     squat
    0.38
     mig
    0.37
     Paste
    0.37
    Activations Density 0.000%

    No Known Activations