© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 51932
    Prev
    Next
    INDEX
    Explanations

    important considerations and rules

    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_31_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
    쩡
    0.41
     Fortunately
    0.38
    OGRAPHY
    0.35
    Fortunately
    0.35
    μένων
    0.34
     Analytical
    0.34
     groovy
    0.33
     Ultimately
    0.33
     }^{(
    0.32
    rokken
    0.32
    POSITIVE LOGITS
     rules
    0.66
     reglas
    0.65
    rules
    0.63
     cautions
    0.61
     Rules
    0.60
    Rules
    0.59
     правила
    0.56
    RULES
    0.56
     regole
    0.55
    规则
    0.54
    Activations Density 0.255%

    No Known Activations