© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63374
    Prev
    Next
    INDEX
    Explanations

    safety and security

    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_41_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
    Dogs
    0.38
    сам
    0.38
    晠
    0.36
    },\
    0.36
    Collector
    0.36
    Overlay
    0.36
    }+...+\
    0.36
    Scenario
    0.35
    }\,
    0.35
    />}
    0.35
    POSITIVE LOGITS
     safety
    1.62
     안전
    1.59
     Safety
    1.56
    安全
    1.55
    Safety
    1.52
    safety
    1.46
     безпе
    1.40
     biztons
    1.39
     安全
    1.38
     SAFETY
    1.37
    Activations Density 0.034%

    No Known Activations