© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 236969
    Prev
    Next
    INDEX
    Explanations

    better, easier, more

    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_25_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
    resist
    0.39
    flipped
    0.38
    P
    0.37
     Hel
    0.37
    bl
    0.37
    larger
    0.36
    Hel
    0.36
    resume
    0.36
    bred
    0.36
    +"
    0.35
    POSITIVE LOGITS
     partenaires
    0.42
     developmentally
    0.40
     _{(
    0.40
     upgrading
    0.39
    ीय
    0.38
     adaptar
    0.37
     Khomeini
    0.37
     repos
    0.37
    ชน์
    0.37
     citas
    0.37
    Activations Density 0.005%

    No Known Activations