© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179367
    Prev
    Next
    INDEX
    Explanations

    Day 1 morning activities

    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_24_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
     imped
    0.48
     impediment
    0.42
    छे
    0.41
     capacit
    0.40
     Ecusson
    0.39
    шу
    0.39
     návr
    0.39
    貳
    0.39
    ಿಸಲು
    0.38
    ídu
    0.38
    POSITIVE LOGITS
    ’
    0.45
    Has
    0.39
    Back
    0.38
     an
    0.38
     l
    0.38
    S
    0.38
    BB
    0.36
    δικ
    0.36
     HO
    0.36
    ott
    0.35
    Activations Density 0.003%

    No Known Activations