© 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-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 9875
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'length', sometimes near words that relate to errors or sizes

    oai_token-act-pair · gemini-2.0-flash

    length

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     itſelf
    -1.63
     purpoſe
    -1.50
     myſelf
    -1.48
     juſt
    -1.40
     houſe
    -1.39
     ſmall
    -1.38
     leaſt
    -1.38
     becauſe
    -1.38
     Efq
    -1.38
     himſelf
    -1.37
    POSITIVE LOGITS
    卉
    0.53
     si
    0.52
    </b>
    0.50
     La
    0.50
     in
    0.48
    informations
    0.48
    gatsby
    0.48
    s
    0.48
     es
    0.47
     arco
    0.47
    Activations Density 1.370%

    No Known Activations