© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17282
    Prev
    Next
    INDEX
    Explanations

    acknowledging diversity, variation within groups

    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_34_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
     bó
    0.38
    oxing
    0.37
    <0x06>
    0.36
     seguro
    0.36
     regl
    0.35
     continents
    0.35
    प्ले
    0.35
    перы
    0.35
    ద
    0.34
     peroxide
    0.34
    POSITIVE LOGITS
     rebel
    0.61
    Collabor
    0.53
     rebels
    0.53
     dissident
    0.49
     moderate
    0.47
    Collaboration
    0.46
     rebellious
    0.46
     Collabor
    0.44
     Collaborate
    0.43
     dissidents
    0.43
    Activations Density 0.027%

    No Known Activations