© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 2811
    Prev
    Next
    INDEX
    Explanations

    supported explanation, observations, Construct

    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_39_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
    珍
    0.44
     adaption
    0.42
    ರಿಸ
    0.41
     ROAD
    0.39
     flats
    0.38
     স্ট
    0.37
     चट
    0.37
    琴
    0.37
    념
    0.36
    
    0.36
    POSITIVE LOGITS
     observations
    0.42
     Leonardo
    0.41
    ultiplier
    0.40
    ignano
    0.40
     prior
    0.39
     Observer
    0.39
     tip
    0.38
     dav
    0.38
     Observations
    0.38
     Objective
    0.37
    Activations Density 0.001%

    No Known Activations