© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 28987
    Prev
    Next
    INDEX
    Explanations

    zero or more times

    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
     poison
    0.46
    poison
    0.46
    㬹
    0.41
     poisoning
    0.40
     Poison
    0.40
     walter
    0.39
    poz
    0.37
     poisonous
    0.37
    Ken
    0.36
     Dont
    0.36
    POSITIVE LOGITS
    bindingFields
    0.41
     Consultancy
    0.40
    clearRect
    0.39
     consultancy
    0.38
     Seaton
    0.38
     реє
    0.37
    田
    0.36
    μι
    0.36
    cadherin
    0.35
     therapies
    0.35
    Activations Density 0.001%

    No Known Activations