© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53473
    Prev
    Next
    INDEX
    Explanations

    car accident collided

    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_31_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
    бие
    0.44
     সব্ব
    0.42
    Ո
    0.39
     Pete
    0.38
    butene
    0.37
    cohols
    0.37
    镣
    0.37
    厓
    0.37
     récupération
    0.36
     अंत
    0.36
    POSITIVE LOGITS
     সুখী
    0.40
     سفر
    0.38
    door
    0.36
     reaching
    0.34
     Smyrna
    0.34
    reaching
    0.33
    Await
    0.33
    Faith
    0.33
     kobi
    0.33
    Door
    0.33
    Activations Density 0.002%

    No Known Activations