© 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. 42161
    Prev
    Next
    INDEX
    Explanations

    Speech-Language Pathologist/Therapy

    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
     can
    0.96
     organize
    0.79
     c
    0.75
     escuchar
    0.74
     threaten
    0.72
     e
    0.72
     regulate
    0.70
     mobilize
    0.70
     distill
    0.70
     tranquilo
    0.70
    POSITIVE LOGITS
    ار
    0.94
    </div>
    0.70
    يد
    0.70
    ت
    0.70
    戊
    0.69
    ol
    0.68
    积
    0.66
    is
    0.66
    一副
    0.64
    telek
    0.63
    Activations Density 0.003%

    No Known Activations