© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199661
    Prev
    Next
    INDEX
    Explanations

    fidelity

    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
     `;
    0.36
     PAL
    0.36
    PWD
    0.36
     Brescia
    0.36
    記
    0.35
    棕
    0.34
    टाम
    0.34
     Pal
    0.34
     Dolly
    0.34
     Prz
    0.33
    POSITIVE LOGITS
     fidelity
    0.49
     আনুগত্য
    0.46
    fidelity
    0.43
    tio
    0.40
     Fidelity
    0.39
    <unused17>
    0.38
     приняли
    0.38
    ometrically
    0.37
    plitude
    0.37
     प्रातः
    0.37
    Activations Density 0.001%

    No Known Activations