© 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. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 211474
    Prev
    Next
    INDEX
    Explanations

    0

    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_43_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
     centrif
    0.42
    Anna
    0.38
     elevator
    0.37
     enriqu
    0.37
    ༦
    0.37
     Punishment
    0.37
    verso
    0.36
     Tops
    0.36
    idev
    0.36
    ضاع
    0.36
    POSITIVE LOGITS
    㤓
    0.38
     Rb
    0.38
    abbe
    0.37
     जे
    0.35
     abe
    0.34
    GroupBy
    0.34
     (!$
    0.34
     ',');
    0.34
    MOUN
    0.34
     بد
    0.33
    Activations Density 0.008%

    No Known Activations