© 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. 63393
    Prev
    Next
    INDEX
    Explanations

    to be

    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
     patience
    0.41
    ensively
    0.41
    ĥ
    0.39
     frisch
    0.39
     Reihen
    0.39
     supera
    0.38
     pře
    0.38
    enga
    0.37
     part
    0.36
    žio
    0.36
    POSITIVE LOGITS
     strong
    1.52
    Strong
    1.49
    strong
    1.48
     Strong
    1.43
    STRONG
    1.40
     STRONG
    1.32
    強
    1.22
     fuerte
    1.20
    强
    1.20
     kuat
    1.18
    Activations Density 0.011%

    No Known Activations