© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200205
    Prev
    Next
    INDEX
    Explanations

    against

    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_46_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
     Land
    0.43
     Ambient
    0.39
     악
    0.39
     engaged
    0.39
     клуб
    0.39
     الخم
    0.38
    Land
    0.38
     ваших
    0.38
     Knob
    0.37
    Ambient
    0.36
    POSITIVE LOGITS
     sabbam
    0.42
    obtenir
    0.40
    estring
    0.39
    那位
    0.39
    folg
    0.38
    icheskij
    0.38
    丏
    0.38
    izzato
    0.38
    這位
    0.38
    擇
    0.38
    Activations Density 0.002%

    No Known Activations