© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200258
    Prev
    Next
    INDEX
    Explanations

    concatenation

    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_12_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
     آتا
    0.28
    报价
    0.26
    Ofer
    0.25
     regalos
    0.24
     nome
    0.24
    Лі
    0.24
    ת
    0.24
    𝓈
    0.24
     naam
    0.24
     regole
    0.24
    POSITIVE LOGITS
    ising
    0.26
    ine
    0.26
    é
    0.24
    en
    0.23
    im
    0.23
    f
    0.23
    in
    0.23
    ere
    0.23
    ut
    0.22
    ong
    0.22
    Activations Density 0.000%

    No Known Activations