© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 3703
    Prev
    Next
    INDEX
    Explanations

    text related to a band's history, including the mention of punk, rock and/or new wave style music

    oai_token-act-pair · gemini-2.0-flash

    Music-related

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    TestingModule
    -0.71
     EdgeInsets
    -0.66
     ddelweddau
    -0.62
    tvguidetime
    -0.59
     باخ
    -0.57
    WriteTagHelper
    -0.56
     UIImageView
    -0.56
    RequestMapping
    -0.56
     seier
    -0.56
    StoryboardSegue
    -0.54
    POSITIVE LOGITS
    ///</
    0.51
    Rè
    0.50
    HtmlAttribute
    0.50
    Substrate
    0.47
     NSCoder
    0.46
    LEncoder
    0.45
    Crossref
    0.45
    Geografie
    0.44
    Rohy
    0.43
     Row
    0.43
    Activations Density 0.401%

    No Known Activations