© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2441
    Prev
    Next
    INDEX
    Explanations

    appearance and atmosphere

    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_39_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
     creș
    0.39
     資
    0.39
    promised
    0.39
     ACTIVITIES
    0.39
    સિ
    0.38
    ocie
    0.38
    jd
    0.38
     rufis
    0.38
    ঝি
    0.37
    bourg
    0.37
    POSITIVE LOGITS
    Emp
    0.40
    Fx
    0.38
    िका
    0.37
     Magic
    0.37
    莒
    0.36
     Empower
    0.36
     மாதிர
    0.36
     насыщен
    0.36
    fx
    0.35
     Edge
    0.35
    Activations Density 0.045%

    No Known Activations