© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1495
    Prev
    Next
    INDEX
    Explanations

    general, common words that might precede a comparison or a change of subject.

    oai_token-act-pair · gemini-2.0-flash

    Conditional statements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     anyone
    -1.23
     Anyone
    -1.16
    anyone
    -1.14
    Anyone
    -1.08
     Anybody
    -1.00
     anybody
    -0.94
    #+#
    -0.94
    Anybody
    -0.83
    FailureListener
    -0.81
     ANYONE
    -0.81
    POSITIVE LOGITS
     anything
    1.10
     Anything
    0.80
    Anything
    0.67
    anything
    0.62
     belo
    0.45
    (>
    0.40
     almost
    0.39
     kalın
    0.39
    odes
    0.39
    атр
    0.39
    Activations Density 1.974%

    No Known Activations