© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 8174
    Prev
    Next
    INDEX
    Explanations

    Tagalog practice or conversation

    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
    ்ப்ப
    2.40
    मित्व
    2.26
     degeneration
    2.23
    tained
    2.21
    en
    2.18
     unconsciously
    2.13
    লেখা
    2.12
    㶲
    2.08
    ්
    2.02
     reviving
    2.01
    POSITIVE LOGITS
    р
    3.33
    ल
    3.20
     хто
    2.48
     кто
    2.37
    のが
    2.35
    सभी
    2.29
    рк
    2.15
    Οι
    2.13
    ره
    2.13
     gång
    2.12
    Activations Density 0.002%

    No Known Activations