© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 219968
    Prev
    Next
    INDEX
    Explanations

    brainstorming, accountability, help

    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_31_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
    穗
    0.37
     assisted
    0.36
    affold
    0.36
     Laat
    0.35
     conscious
    0.35
     Enlight
    0.35
    assisted
    0.34
     Gond
    0.34
    %)
    0.34
     Zhen
    0.34
    POSITIVE LOGITS
     unanimously
    0.46
    摷
    0.41
     menawarkan
    0.38
    டுகின்றன
    0.38
     ofrecen
    0.38
     предлага
    0.38
     metá
    0.37
     adversaries
    0.37
     intereses
    0.36
    螞
    0.36
    Activations Density 0.002%

    No Known Activations