© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6660
    Prev
    Next
    INDEX
    Explanations

    words related to sounds and sensory experiences

    oai_token-act-pair · gemini-2.0-flash

    senses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    GEBURTS
    -0.69
    Geplaatst
    -0.56
    istoitu
    -0.51
     Paglinawan
    -0.50
    archiviato
    -0.50
    )}$
    -0.48
    ecido
    -0.47
    TAGS
    -0.47
    )}$.
    -0.47
    )}$,
    -0.45
    POSITIVE LOGITS
     hearing
    0.97
     smell
    0.93
     hear
    0.92
    smell
    0.90
     sound
    0.89
    hear
    0.86
     Hearing
    0.85
    hearing
    0.85
     hears
    0.85
     HEARING
    0.79
    Activations Density 0.872%

    No Known Activations