© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227732
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_6_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
    و
    0.93
    as
    0.82
    dır
    0.76
    lz
    0.75
    larda
    0.73
    da
    0.67
    ために
    0.66
    u
    0.65
    lardan
    0.64
    на
    0.63
    POSITIVE LOGITS
     hypothes
    0.73
    </h6>
    0.65
     categor
    0.61
    </h3>
    0.61
    </h1>
    0.59
    \
    0.56
    </h4>
    0.55
    </u>
    0.54
     synchron
    0.54
    </h2>
    0.54
    Activations Density 0.000%

    No Known Activations