© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31922
    Prev
    Next
    INDEX
    Explanations

    being there when needed

    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_31_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
    泾
    0.38
    مني
    0.36
    ጐ
    0.36
    ุง
    0.35
    奖励
    0.35
    衡
    0.35
    someone
    0.34
    rā
    0.33
    纽
    0.33
    维护
    0.33
    POSITIVE LOGITS
     request
    0.38
    Attk
    0.38
     strive
    0.37
     anguish
    0.37
    bedarf
    0.37
     alo
    0.37
     notification
    0.36
     endeavor
    0.36
    जूद
    0.35
     tiz
    0.35
    Activations Density 0.010%

    No Known Activations