© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41858
    Prev
    Next
    INDEX
    Explanations

    system includes

    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_22_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
    }
    0.21
     U
    0.20
    の
    0.19
    確
    0.19
     drawback
    0.19
     triang
    0.18
     =
    0.18
    ixon
    0.18
     dode
    0.18
     frameworks
    0.18
    POSITIVE LOGITS
     começou
    0.23
    ันทร์
    0.23
    🍳
    0.21
    ètement
    0.21
     ليها
    0.21
     diaphr
    0.20
     Typh
    0.20
     Sheehan
    0.20
    ্বাদ
    0.20
     Nolan
    0.19
    Activations Density 0.000%

    No Known Activations