© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 40209
    Prev
    Next
    INDEX
    Explanations

    p

    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_57_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
    usay
    0.47
    utig
    0.44
    оп
    0.43
     оп
    0.41
    us
    0.41
    uncia
    0.40
    мне
    0.40
    骥
    0.40
    üs
    0.40
     মিনি
    0.39
    POSITIVE LOGITS
    rec
    0.59
    rack
    0.59
    red
    0.56
    redi
    0.55
    rax
    0.55
    réd
    0.50
    rem
    0.50
    redd
    0.50
    rak
    0.48
    rail
    0.48
    Activations Density 0.006%

    No Known Activations