© 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. 14262
    Prev
    Next
    INDEX
    Explanations

    chose/why

    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
     Menc
    0.38
     suck
    0.36
     ['(?
    0.34
     Mend
    0.33
     Cors
    0.33
    пот
    0.33
     たら
    0.32
     ï
    0.32
    ങ്ക
    0.32
     fancy
    0.32
    POSITIVE LOGITS
    chosen
    1.56
     chosen
    1.55
     chose
    1.51
     Chosen
    1.38
     escolh
    1.38
     dipilih
    1.38
     choisi
    1.35
     выбрали
    1.34
     scelto
    1.33
    Chosen
    1.32
    Activations Density 0.283%

    No Known Activations