© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206355
    Prev
    Next
    INDEX
    Explanations

    interest of

    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
    is
    1.75
    al
    1.45
    en
    1.44
    Y
    1.38
    on
    1.35
    u
    1.34
    m
    1.34
    er
    1.30
    ah
    1.30
    id
    1.27
    POSITIVE LOGITS
     arbres
    1.02
     écl
    0.91
     antigens
    0.87
     cornice
    0.87
     fragments
    0.86
     conseils
    0.86
     cannabinoids
    0.86
     particles
    0.85
     eccles
    0.84
     atoms
    0.83
    Activations Density 0.000%

    No Known Activations