© 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. 14705
    Prev
    Next
    INDEX
    Explanations

    the word "Mount" followed by a capitalized word, or the abbreviation "Mt."

    oai_token-act-pair · gemini-2.0-flash

    the term 'Mount'

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

    mountain

    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
    Lähteet
    -0.47
    addGap
    -0.46
    mobileqq
    -0.43
     inter
    -0.42
     Lumpur
    -0.41
    autorité
    -0.41
    <bos>
    -0.41
     확인함
    -0.40
    müş
    -0.39
    inter
    -0.38
    POSITIVE LOGITS
    SBATCH
    0.81
    StoreMessageInfo
    0.73
    roek
    0.69
     للاسماء
    0.65
     typelib
    0.65
    IonicModule
    0.65
    __":
    0.65
     protoimpl
    0.64
    IPAC
    0.63
    InstanceState
    0.62
    Activations Density 0.264%

    No Known Activations