© 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. 30868
    Prev
    Next
    INDEX
    Explanations

    greeting followed by question or statement

    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
     grease
    0.41
     hugs
    0.38
     cyclohex
    0.37
    ጴ
    0.37
     hug
    0.37
     পাগ
    0.37
     табле
    0.37
    羿
    0.36
    Sup
    0.36
    Angular
    0.36
    POSITIVE LOGITS
     CBD
    0.60
     cbd
    0.52
     Cbd
    0.50
    CBD
    0.47
    cbd
    0.45
     Hemp
    0.45
     hemp
    0.41
     પે
    0.38
     DOE
    0.38
    estell
    0.38
    Activations Density 0.006%

    No Known Activations