© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205815
    Prev
    Next
    INDEX
    Explanations

    abonnement, every way, dichotomies

    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_6_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
    ру
    1.19
    и
    1.07
    ни
    1.06
     in
    1.05
    waiting
    1.05
    1
    1.03
    는
    1.02
    li
    0.98
    ่
    0.97
    ي
    0.97
    POSITIVE LOGITS
     añad
    1.07
     ampli
    0.99
     парла
    0.99
     други
    0.97
    ف
    0.97
     казни
    0.94
     algorit
    0.93
     твор
    0.92
     conclu
    0.92
    앜
    0.91
    Activations Density 0.000%

    No Known Activations