© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 229362
    Prev
    Next
    INDEX
    Explanations

    address

    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_57_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
     AD
    0.51
    AAD
    0.51
    AD
    0.51
     А
    0.50
     阿
    0.50
    AID
    0.50
    APD
    0.50
    AN
    0.49
    阿
    0.48
     Ад
    0.47
    POSITIVE LOGITS
     Ter
    0.41
    Set
    0.40
    Ĩ
    0.40
     Ki
    0.40
     Бере
    0.39
     Emit
    0.38
     Set
    0.38
     Rel
    0.38
    𝙸
    0.38
     Invoke
    0.38
    Activations Density 0.000%

    No Known Activations