© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7789
    Prev
    Next
    INDEX
    Explanations

    positive reviews, especially those about food or style

    oai_token-act-pair · gemini-2.0-flash

    foreign language

    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
    ьаж
    -0.60
     polyps
    -0.59
     monomers
    -0.59
     demurrer
    -0.57
     proofs
    -0.57
    bootstrapcdn
    -0.56
     supernatant
    -0.56
     unknownFields
    -0.54
     überzeugt
    -0.54
     Proofs
    -0.54
    POSITIVE LOGITS
    ברס
    0.50
     AudioSource
    0.47
    ‚¬
    0.47
    stens
    0.46
     Singer
    0.46
    Einzelnachweise
    0.46
    semantics
    0.45
    ogenen
    0.44
     chấm
    0.44
    PreExecute
    0.44
    Activations Density 2.105%

    No Known Activations