© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 231169
    Prev
    Next
    INDEX
    Explanations

    async function

    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_6_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
    an
    1.45
    ed
    1.34
    ers
    1.20
    als
    1.15
    ion
    1.13
    ors
    1.13
    ess
    1.12
    _
    1.11
    ip
    1.07
    ial
    1.06
    POSITIVE LOGITS
     have
    1.42
     في
    1.16
     a
    1.07
     conclude
    1.06
     к
    1.05
     возь
    1.04
     occupy
    1.03
    في
    1.02
     constitute
    1.02
     compete
    1.01
    Activations Density 0.001%

    No Known Activations