Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 5-GEMMASCOPE-2-TRANSCODER-262K
    4. 4901
    Prev
    Next
    INDEX
    Explanations

    testing and example code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_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
    мента
    0.63
    l
    0.49
     tym
    0.46
    adidas
    0.46
    ″
    0.44
    Americans
    0.44
     Americans
    0.43
     bcrypt
    0.43
     Evam
    0.42
    CONCLUSION
    0.42
    POSITIVE LOGITS
    ཝ
    0.52
    ཋ
    0.51
     loudspeaker
    0.51
    ධාන
    0.50
    }^{-\
    0.49
     ڈاک
    0.48
    ારો
    0.48
    ocat
    0.47
    áš
    0.47
    ܟ
    0.47
    Activations Density 0.051%

    No Known Activations