© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 89493
    Prev
    Next
    INDEX
    Explanations

    able to do something

    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_23_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
    ści
    0.50
    ḏ
    0.45
    AOrdenar
    0.45
    ̻
    0.42
    🫢
    0.41
    ander
    0.40
     играть
    0.39
    ANDER
    0.39
    anders
    0.39
    _{+}\
    0.39
    POSITIVE LOGITS
     vetting
    0.46
     consolidation
    0.42
     vetted
    0.41
     непро
    0.39
     Anywhere
    0.38
     ability
    0.37
     Parkway
    0.37
     classroom
    0.37
     Ein
    0.37
    ကာ
    0.37
    Activations Density 0.004%

    No Known Activations