© 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. 46089
    Prev
    Next
    INDEX
    Explanations

    work from home

    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
     elenco
    0.85
     amoureux
    0.78
    ম
    0.74
     obiettivo
    0.73
    ش
    0.73
     espace
    0.72
     idioma
    0.71
    y
    0.71
     histoire
    0.70
     immagine
    0.70
    POSITIVE LOGITS
    きた
    0.69
    trad
    0.68
    thesis
    0.68
    td
    0.63
    raz
    0.63
    div
    0.62
    dy
    0.61
    allo
    0.60
     was
    0.59
    iven
    0.59
    Activations Density 0.007%

    No Known Activations