© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 121847
    Prev
    Next
    INDEX
    Explanations

    attic or roof

    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_37_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
     নয়ন
    0.42
    瑩
    0.39
    ordination
    0.37
     xr
    0.37
     canyon
    0.36
    fidelity
    0.36
    磷
    0.36
    స్త్ర
    0.36
    硚
    0.36
    ytes
    0.35
    POSITIVE LOGITS
     attic
    1.30
     Attic
    1.13
     loft
    0.97
     att
    0.87
     roof
    0.84
     Loft
    0.83
    loft
    0.78
     Roof
    0.74
    Roof
    0.72
    Att
    0.71
    Activations Density 0.023%

    No Known Activations