© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 167021
    Prev
    Next
    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    zano
    0.34
    jax
    0.34
    ė
    0.33
    But
    0.33
    dm
    0.33
    დომ
    0.33
    бері
    0.32
    Comment
    0.32
     Hero
    0.32
    redi
    0.32
    POSITIVE LOGITS
    或
    1.26
     или
    1.17
     or
    1.16
    หรือ
    1.16
     বা
    1.11
     ಅಥವಾ
    1.07
     hoặc
    1.05
     અથવા
    1.02
     அல்லது
    1.00
     或
    0.98
    Activations Density 0.001%

    No Known Activations