© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9055
    Prev
    Next
    INDEX
    Explanations

    words about singing or opera, including descriptions of the qualities of a singer's voice.

    oai_token-act-pair · gemini-2.0-flash

    specific song or observation keywords

    np_token-act-pair-logits · gpt-4o-mini

    songs and music

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     Atem
    -0.45
     صوتيه
    -0.44
    vejte
    -0.43
    danno
    -0.43
    Vide
    -0.43
    _))
    -0.43
     Pach
    -0.43
    idió
    -0.43
     rheumatism
    -0.42
    ที่ยว
    -0.42
    POSITIVE LOGITS
    $_['
    0.62
    ########.
    0.61
    flashdata
    0.57
     song
    0.56
     observation
    0.55
    IndentedString
    0.55
    lug
    0.54
    oredCriteria
    0.54
    jooq
    0.54
    observation
    0.52
    Activations Density 1.382%

    No Known Activations