© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2900
    Prev
    Next
    INDEX
    Explanations

    percentage values

    oai_token-act-pair · gemini-2.0-flash

    percent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     تانيه
    -0.83
    AddTagHelper
    -0.73
     BoxDecoration
    -0.71
     defaultstate
    -0.69
     cał
    -0.68
    })*/
    -0.65
     '\\;'
    -0.65
    ]")]
    -0.64
     MainAxisSize
    -0.64
     Jefus
    -0.63
    POSITIVE LOGITS
     Schar
    0.51
    NOPQRST
    0.45
    bille
    0.44
     labios
    0.44
     impos
    0.43
     Fair
    0.42
    HasOne
    0.42
    quam
    0.41
     final
    0.41
    bric
    0.40
    Activations Density 4.508%

    No Known Activations