© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53858
    Prev
    Next
    INDEX
    Explanations

    level=

    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_31_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
    ｘ
    0.40
    ään
    0.40
     മണിക്ക
    0.39
    oot
    0.38
     decade
    0.38
    ('--
    0.37
     भाव
    0.37
    <td>
    0.36
    '^
    0.36
    ibilità
    0.35
    POSITIVE LOGITS
     Niveau
    0.54
    Level
    0.54
     Level
    0.51
     poziomie
    0.48
     level
    0.48
     nível
    0.47
     tingkat
    0.44
     niveau
    0.42
    レベル
    0.42
     уровне
    0.42
    Activations Density 0.001%

    No Known Activations