© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54086
    Prev
    Next
    INDEX
    Explanations

    extracting, writing, naming

    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_30_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
    ND
    0.30
    End
    0.27
    ç
    0.26
    low
    0.25
    MONT
    0.25
    N
    0.25
    mean
    0.25
    Merry
    0.25
    BO
    0.24
    L
    0.24
    POSITIVE LOGITS
     automating
    0.31
     changeable
    0.26
     extracting
    0.26
     informática
    0.26
     insect
    0.26
    েনার
    0.26
     automaty
    0.26
     automate
    0.26
     Automat
    0.25
     Computational
    0.25
    Activations Density 0.049%

    No Known Activations