© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10789
    Prev
    Next
    INDEX
    Explanations

    uses equations, functions, and code

    oai_token-act-pair · gemini-2.0-flash

    functional

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     m
    -0.51
     J
    -0.50
    …
    -0.48
     d
    -0.47
    ↵↵
    -0.47
    ct
    -0.44
     g
    -0.44
    loxy
    -0.44
     David
    -0.44
     []:
    -0.43
    POSITIVE LOGITS
     itſelf
    1.04
     Houſe
    0.99
     كومونز
    0.92
     poffible
    0.92
     myſelf
    0.91
     houſe
    0.91
     Monfieur
    0.90
     Efq
    0.88
     Majefty
    0.85
     purpoſe
    0.84
    Activations Density 7.759%

    No Known Activations