© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14160
    Prev
    Next
    INDEX
    Explanations

    tasks

    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_34_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
    ល់
    0.40
    伞
    0.39
    ૭
    0.38
     twitch
    0.37
    ecan
    0.37
    orang
    0.37
     reç
    0.36
    left
    0.36
    লাম
    0.36
    ர்த்து
    0.36
    POSITIVE LOGITS
     happening
    0.50
     odby
    0.39
     відбувається
    0.38
     происходит
    0.38
    🖒
    0.37
     проис
    0.36
     আতঙ্ক
    0.36
     நடைபெறும்
    0.36
     Affect
    0.35
    发生在
    0.35
    Activations Density 0.124%

    No Known Activations