© 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. 167531
    Prev
    Next
    INDEX
    Explanations

    water vapor/droplets

    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
    fine
    0.67
    Fine
    0.67
     fine
    0.63
     respir
    0.63
     equ
    0.61
     FINE
    0.60
    细
    0.56
    FINE
    0.55
    細
    0.51
     Fine
    0.50
    POSITIVE LOGITS
     routing
    0.40
     biased
    0.39
     biasing
    0.39
     queuing
    0.38
     Garden
    0.38
     biases
    0.38
    igg
    0.37
     garden
    0.37
     kartu
    0.37
     filed
    0.36
    Activations Density 0.005%

    No Known Activations