© 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. 63391
    Prev
    Next
    INDEX
    Explanations

    Gaussian process, machine learning, methods

    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
     لینے
    0.50
    앵
    0.40
    ]).
    0.40
     thấy
    0.38
    UTIONS
    0.38
    سباب
    0.37
    浿
    0.37
    ].)
    0.36
    呠
    0.36
     Convertible
    0.36
    POSITIVE LOGITS
     Middlesbrough
    0.47
     Tees
    0.45
     discour
    0.41
    Cleveland
    0.38
     Zil
    0.38
     Ende
    0.38
     medio
    0.38
     Tee
    0.38
    amo
    0.38
     Middles
    0.37
    Activations Density 0.000%

    No Known Activations