© 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-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13603
    Prev
    Next
    INDEX
    Explanations

    academic text with citations, analyses, and results

    oai_token-act-pair · gemini-2.0-flash

    uncertainty and conditions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     BoxFit
    -0.68
    .*")]
    -0.55
    JOptionPane
    -0.50
    ولايات
    -0.47
    собенно
    -0.47
    orsch
    -0.47
    ]")]
    -0.45
    бычно
    -0.44
    imageio
    -0.43
     ModelExpression
    -0.42
    POSITIVE LOGITS
     given
    3.48
    given
    3.14
     Given
    2.89
    Given
    2.86
     GIVEN
    2.56
     dado
    1.86
     dadas
    1.63
     donné
    1.58
     donnée
    1.55
     dada
    1.53
    Activations Density 10.765%

    No Known Activations