© 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. 134622
    Prev
    Next
    INDEX
    Explanations

    solitaire games and diamond rings

    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
    us
    1.26
    de
    1.19
    z
    1.18
    ire
    1.09
    ug
    1.08
    (\
    1.05
    на
    1.03
    cs
    1.03
    ng
    1.02
    sp
    1.01
    POSITIVE LOGITS
     tenido
    1.02
    </h3>
    1.00
     tenia
    0.97
     ממ
    0.93
     raiz
    0.93
     frío
    0.91
     pièce
    0.90
     demora
    0.90
    ↵
    0.89
     posto
    0.89
    Activations Density 0.000%

    No Known Activations