© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 13834
    Prev
    Next
    INDEX
    Explanations

    LaTeX markup and mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    $

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.62
     jScrollPane
    -0.60
    ArgsConstructor
    -0.59
    userdetails
    -0.56
    Clik
    -0.53
    Cursors
    -0.52
    toplankton
    -0.51
    Shots
    -0.51
    yntaxException
    -0.51
     tán
    -0.50
    POSITIVE LOGITS
    esModule
    0.57
    defineProperty
    0.54
     parabola
    0.52
    endif
    0.52
    RefNanny
    0.50
     Pythagorean
    0.50
     endif
    0.50
    Xna
    0.50
     насеље
    0.49
    “……”
    0.49
    Activations Density 16.812%

    No Known Activations