© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 41066
    Prev
    Next
    INDEX
    Explanations

    hijabi woman Spartan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    '
    0.93
    iques
    0.74
    .
    0.74
    \
    0.72
    ing
    0.71
    ed
    0.69
    ania
    0.65
    ihu
    0.64
    Bias
    0.63
    ৫
    0.63
    POSITIVE LOGITS
     precipitated
    0.68
    é
    0.68
     motionless
    0.67
     gravité
    0.67
     particulier
    0.66
    }$.
    0.65
    ڊ
    0.65
     conduite
    0.65
    ю
    0.65
     proche
    0.64
    Activations Density 0.002%

    No Known Activations