© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201923
    Prev
    Next
    INDEX
    Explanations

    offerings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    itano
    0.36
     ensayo
    0.36
     inflating
    0.36
     वास
    0.35
    とその
    0.34
    ILTON
    0.33
    idle
    0.33
    >?,
    0.33
     quantitative
    0.32
     stitched
    0.32
    POSITIVE LOGITS
    Offering
    2.84
     Offering
    2.80
     offering
    2.77
     offerings
    2.59
    Offer
    2.48
     Offer
    2.44
    offer
    2.41
     OFFER
    2.36
     offer
    2.27
     oferta
    2.19
    Activations Density 0.056%

    No Known Activations