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. 25-GEMMASCOPE-2-TRANSCODER-262K
    4. 8574
    Prev
    Next
    INDEX
    Explanations

    call

    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
    chemical
    0.69
    복
    0.66
    subtitle
    0.66
    ScriptName
    0.66
    writeObject
    0.66
     клиен
    0.63
     सुनहरा
    0.63
     பொருட்க
    0.62
    ട്ടി
    0.62
    叮
    0.62
    POSITIVE LOGITS
     call
    1.26
     Calls
    1.19
     calls
    1.16
     make
    1.13
    Calls
    1.13
    call
    1.09
     Call
    1.09
    calls
    1.07
     makes
    1.05
    Call
    1.04
    Activations Density 0.141%

    No Known Activations