© 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. 7369
    Prev
    Next
    INDEX
    Explanations

    natural language processing

    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
    า
    2.41
     capita
    2.28
    an
    2.28
     Além
    2.26
     obese
    2.25
    }]$
    2.23
    ging
    2.22
    ,\,\
    2.21
    ilation
    2.11
    ,\,\,\,\
    2.07
    POSITIVE LOGITS
    ه
    2.45
    на
    2.20
     hali
    2.10
    ी
    2.05
     coppia
    2.04
    leistungen
    2.03
    hasil
    2.01
    ுமி
    1.97
    𝚖
    1.93
     pięk
    1.93
    Activations Density 0.087%

    No Known Activations