© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 122832
    Prev
    Next
    INDEX
    Explanations

    let's have

    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_3_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
     receive
    0.60
    ]
    0.59
     find
    0.57
    <td>
    0.57
     report
    0.57
    다
    0.55
     Netz
    0.55
    al
    0.55
     Midway
    0.55
    th
    0.54
    POSITIVE LOGITS
    م
    0.80
     anisotrop
    0.75
    ens
    0.74
    ST
    0.72
    не
    0.70
     allons
    0.70
     énerg
    0.70
     elett
    0.69
    𝒎
    0.68
     irreducible
    0.68
    Activations Density 0.001%

    No Known Activations