© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233150
    Prev
    Next
    INDEX
    Explanations

    employment or other opportunities

    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_32_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
    very
    0.42
    arg
    0.35
    ",[
    0.35
    лект
    0.34
    import
    0.33
     screened
    0.33
     പാല
    0.33
    许
    0.33
    includes
    0.32
    ession
    0.32
    POSITIVE LOGITS
     जश्न
    0.38
     Counters
    0.38
     Durable
    0.37
     condición
    0.36
    dihydroxy
    0.36
    反正
    0.35
    }=$
    0.35
    സു
    0.35
     translateY
    0.35
    ܀
    0.35
    Activations Density 0.001%

    No Known Activations