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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 5061
    Prev
    Next
    INDEX
    Explanations

    programming application

    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
    ুর
    2.45
    𝚞
    2.28
    ieving
    2.24
    igation
    2.07
    𝚘
    2.04
    ة
    2.01
     curtains
    2.01
    ುದು
    2.00
     acaso
    1.98
    мов
    1.96
    POSITIVE LOGITS
    u
    2.51
    usize
    2.46
    screen
    2.34
    esper
    2.34
    gcd
    2.23
    шње
    2.19
    تى
    2.16
    cısı
    2.16
    માં
    2.12
     onBackPressed
    2.08
    Activations Density 0.014%

    No Known Activations