© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82539
    Prev
    Next
    INDEX
    Explanations

    Prince

    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_53_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
    ilibre
    0.42
    莳
    0.41
     dangle
    0.38
    molecule
    0.38
    യില്ല
    0.38
    низу
    0.37
    ikey
    0.36
    diyl
    0.36
     explanatory
    0.36
    Art
    0.35
    POSITIVE LOGITS
     Prince
    0.48
    zok
    0.44
    Prince
    0.43
    给定
    0.42
     evidente
    0.40
     prince
    0.39
    *}$
    0.39
     PRIN
    0.38
    เนื้อ
    0.37
    +}
    0.37
    Activations Density 0.001%

    No Known Activations