© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15492
    Prev
    Next
    INDEX
    Explanations

    mentions of a speaking voice in dialog or a digital assistant

    oai_token-act-pair · gemini-2.0-flash

    text related to voice technology

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

    voice

    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
    Negative Logits
    yntaxException
    -0.45
     beginnetje
    -0.45
    nya
    -0.45
    преде
    -0.41
    REG
    -0.40
     Har
    -0.40
    المكان
    -0.40
    yethyl
    -0.40
    ēm
    -0.40
    ányi
    -0.40
    POSITIVE LOGITS
    pexpr
    0.72
    ثيق
    0.65
    WriteTagHelper
    0.65
     désolés
    0.62
    +#+#
    0.62
    ########.
    0.60
     MTN
    0.60
    rungsseite
    0.60
    っきり
    0.59
    nocache
    0.59
    Activations Density 2.381%

    No Known Activations