© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 87807
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_18_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
    ま
    0.47
    rd
    0.46
     revolutionary
    0.46
     um
    0.45
     very
    0.45
     monet
    0.44
     mixed
    0.43
     house
    0.43
     revolution
    0.42
    ae
    0.42
    POSITIVE LOGITS
    íduos
    0.50
     effectuées
    0.47
    荅
    0.47
     segurança
    0.46
    urón
    0.46
     ఏర్పాటు
    0.46
    맺
    0.45
     Algeria
    0.45
    =\$
    0.45
     Stability
    0.45
    Activations Density 0.000%

    No Known Activations