© 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. 6018
    Prev
    Next
    INDEX
    Explanations

    the fact that

    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
    er
    1.53
    ು
    1.48
    erad
    1.38
    Jika
    1.30
     spanned
    1.28
    ක්
    1.28
     відповід
    1.25
     okvir
    1.25
    若
    1.25
    ಮ
    1.25
    POSITIVE LOGITS
     `>`,
    1.51
    чать
    1.25
    가
    1.20
    ்டர்
    1.20
     género
    1.19
    emente
    1.17
    oglobine
    1.13
     alimentar
    1.13
    elser
    1.12
    orragie
    1.10
    Activations Density 0.022%

    No Known Activations