© 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. 75777
    Prev
    Next
    INDEX
    Explanations

    I followed by a verb

    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
     συμ
    0.40
     हां
    0.37
    }[(
    0.36
     우선
    0.36
     Apparently
    0.36
     Dreh
    0.36
    Sched
    0.35
    偶
    0.35
    getRedTeam
    0.35
    獻
    0.35
    POSITIVE LOGITS
    examin
    0.44
    smiling
    0.39
     коммуника
    0.39
     liberty
    0.38
    lib
    0.37
     brillant
    0.36
     قرب
    0.36
     libera
    0.36
     путеше
    0.35
     リー
    0.35
    Activations Density 0.001%

    No Known Activations