© 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. 8294
    Prev
    Next
    INDEX
    Explanations

    write down

    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
    ам
    1.82
    ме
    1.82
    as
    1.61
    ном
    1.61
    ным
    1.57
     нем
    1.48
    у
    1.47
    ного
    1.46
    ла
    1.43
    ो
    1.39
    POSITIVE LOGITS
     aloud
    1.49
     coerc
    1.48
    ி
    1.45
    <td>
    1.41
     இல்
    1.39
    }${
    1.38
    旛
    1.37
    म
    1.36
     दाखिल
    1.35
     prevalence
    1.35
    Activations Density 0.128%

    No Known Activations