© 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. 3406
    Prev
    Next
    INDEX
    Explanations

    numbers and location-related terms

    oai_token-act-pair · gemini-2.0-flash

    words or patterns related to data listings

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

    References to numbers/counting

    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
    contentLoaded
    -0.81
    Personensuche
    -0.74
    MigrationBuilder
    -0.74
     resourceCulture
    -0.70
     snippetHide
    -0.69
     $_"
    -0.68
    }]
    -0.68
    ]--;
    -0.67
    ."],
    -0.66
    ayaquil
    -0.65
    POSITIVE LOGITS
     îns
    0.49
    ManyToMany
    0.46
    чними
    0.43
     x
    0.42
    НИ
    0.42
    itemize
    0.42
    ||}
    0.41
    list
    0.41
    ãng
    0.41
     chevaux
    0.41
    Activations Density 1.569%

    No Known Activations