© 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. 166944
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
     child
    0.70
    child
    0.67
     Child
    0.64
    Child
    0.59
    子
    0.58
     CHILD
    0.55
     子
    0.54
    子が
    0.49
    子的
    0.48
    子上
    0.46
    POSITIVE LOGITS
    IPS
    0.40
     sons
    0.38
     angry
    0.37
    mathbf
    0.36
     boys
    0.36
    Boys
    0.35
    oked
    0.35
    露出
    0.35
     disgusted
    0.35
    user
    0.34
    Activations Density 0.001%

    No Known Activations