© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36176
    Prev
    Next
    INDEX
    Explanations

    house styles and types

    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_11_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
    </h3>
    0.65
    </h5>
    0.60
    <strong>
    0.59
    </strong>
    0.57
     Québec
    0.54
     Café
    0.54
     jakości
    0.54
     déliv
    0.52
     Russ
    0.52
    ICE
    0.52
    POSITIVE LOGITS
     bungalows
    0.70
    ⺈
    0.59
     optima
    0.58
    เอง
    0.55
     bungal
    0.55
     bungalow
    0.55
     mansions
    0.55
     dwellings
    0.53
    драт
    0.52
    жка
    0.51
    Activations Density 0.020%

    No Known Activations