© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8555
    Prev
    Next
    INDEX
    Explanations

    later or earlier in time

    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_3_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
    ங்கிணை
    2.79
    u
    2.68
     인한
    2.60
     retaliation
    2.55
    withstanding
    2.53
    
    2.48
    ForeColor
    2.45
     posibilidad
    2.37
    opportun
    2.32
    𝘶
    2.32
    POSITIVE LOGITS
    ка
    3.17
    יו
    2.73
    te
    2.69
    ά
    2.52
    ত্বের
    2.49
    meny
    2.47
    ون
    2.45
    ്
    2.43
    य
    2.42
     anului
    2.41
    Activations Density 0.039%

    No Known Activations