© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 202983
    Prev
    Next
    INDEX
    Explanations

    it

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     არის
    0.42
     είναι
    0.40
     इट्स
    0.40
     theres
    0.39
     isnt
    0.39
    బాటు
    0.38
    submission
    0.37
    現
    0.37
    henes
    0.36
     Managers
    0.36
    POSITIVE LOGITS
     say
    0.49
     talking
    0.48
     اقول
    0.45
     మాట్లాడుతూ
    0.45
     говорить
    0.40
    Says
    0.40
     aho
    0.39
     telling
    0.39
    }}+\
    0.38
     saying
    0.38
    Activations Density 0.004%

    No Known Activations