© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27873
    Prev
    Next
    INDEX
    Explanations

    media queries

    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_40_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
    HintPath
    0.40
     minima
    0.39
    Job
    0.37
    grammar
    0.37
    像
    0.37
     Polyp
    0.35
     (()
    0.35
     Job
    0.35
    NAP
    0.34
    EXTRA
    0.34
    POSITIVE LOGITS
     maksymal
    0.50
     максимум
    0.46
     अधिकतम
    0.44
    ents
    0.41
     максима
    0.41
     সর্বোচ্চ
    0.41
     管
    0.40
     maksimal
    0.40
    amax
    0.40
    的最大
    0.40
    Activations Density 0.000%

    No Known Activations