© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150649
    Prev
    Next
    INDEX
    Explanations

    reducing costs

    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_23_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
    fer
    0.44
    liquer
    0.40
    ukam
    0.40
    Fer
    0.40
    iffer
    0.39
    intendent
    0.38
     wouldnt
    0.38
    廪
    0.37
    лим
    0.37
    चुर
    0.37
    POSITIVE LOGITS
    星座
    0.38
    hadow
    0.38
     constellation
    0.38
     revolutionary
    0.37
     derail
    0.37
     සො
    0.36
     revolutionized
    0.35
     tue
    0.35
     روشن
    0.35
     unemployment
    0.35
    Activations Density 0.004%

    No Known Activations