© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11200
    Prev
    Next
    INDEX
    Explanations

    the words "pop up" and words related to writing/presenting content, coupled with legal terminology and words indicating failure to appear.

    oai_token-act-pair · gemini-2.0-flash

    Things appearing/problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     appeared
    -2.31
     appearing
    -2.19
     appearance
    -2.00
    appeared
    -1.98
     APPE
    -1.97
     appear
    -1.91
     Appearance
    -1.89
    appear
    -1.86
     Appear
    -1.85
    appearing
    -1.80
    POSITIVE LOGITS
    ندي
    0.48
     akt
    0.42
    ereço
    0.42
     enco
    0.42
    issau
    0.41
    GIH
    0.40
    ंदु
    0.40
    iliary
    0.40
    uten
    0.40
     aco
    0.39
    Activations Density 2.105%

    No Known Activations