© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120024
    Prev
    Next
    INDEX
    Explanations

    ascending or descending order

    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_27_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
     मूव
    0.39
    idefinite
    0.38
     собстве
    0.38
    lower
    0.38
    serialized
    0.38
    shifting
    0.37
    穼
    0.37
     Lower
    0.37
    隐含
    0.37
     Native
    0.37
    POSITIVE LOGITS
    ዢ
    0.38
    গে
    0.37
    STATES
    0.36
    ЕМ
    0.36
     incont
    0.35
     করিত
    0.34
    POINTS
    0.34
     spore
    0.34
    不錯
    0.33
     unveils
    0.33
    Activations Density 0.005%

    No Known Activations