© 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. 10900
    Prev
    Next
    INDEX
    Explanations

    code-like text with numbers, letters, brackets and certain variable names

    oai_token-act-pair · gemini-2.0-flash

    zero or value

    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
     Efq
    -1.20
     myſelf
    -1.16
     iſt
    -1.09
    ^(@)
    -1.09
     Monfieur
    -1.04
     ſeveral
    -1.01
     itſelf
    -1.01
     purpoſe
    -0.99
     themſelves
    -0.94
     $_"
    -0.94
    POSITIVE LOGITS
    <eos>
    0.53
    0
    0.52
    èlement
    0.48
    xe
    0.47
    ד
    0.46
    ym
    0.45
    gt
    0.45
    gs
    0.45
    ="../../
    0.45
    <td>
    0.43
    Activations Density 2.273%

    No Known Activations