© 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. 123222
    Prev
    Next
    INDEX
    Explanations

    glass and steel

    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
    ট
    0.72
    煐
    0.70
    Able
    0.69
    মধ্যে
    0.67
    驩
    0.66
    槁
    0.65
    sinh
    0.64
    sonian
    0.64
    炤
    0.63
    sin
    0.62
    POSITIVE LOGITS
     is
    0.91
    ↵↵
    0.84
     of
    0.81
    oton
    0.70
    er
    0.68
    ika
    0.67
    5
    0.66
    eyes
    0.66
    ↵↵↵
    0.65
    ung
    0.64
    Activations Density 0.000%

    No Known Activations