© 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-3-4B-IT
    5. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 9048
    Prev
    Next
    INDEX
    Explanations

    attribute

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_25_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
    Tower
    0.75
     Tower
    0.69
    พื้นที่
    0.68
     tower
    0.67
    だい
    0.65
     verst
    0.65
    প্রিল
    0.65
    ค
    0.64
     tanque
    0.64
     Bouchard
    0.64
    POSITIVE LOGITS
     attribute
    3.54
     Attribute
    3.26
     attributes
    3.18
    attribute
    3.17
     attributed
    3.09
     attribu
    3.08
    Attribute
    3.06
     attributing
    3.03
     Attributes
    2.94
     atribu
    2.89
    Activations Density 0.391%

    No Known Activations