© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3673
    Prev
    Next
    INDEX
    Explanations

    the words "physical", "psychological," and "mental."

    oai_token-act-pair · gemini-2.0-flash

    concepts related to physical health

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

    physical

    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
    SourceChecksum
    -0.85
    Tikang
    -0.79
    migrationBuilder
    -0.77
    Personendaten
    -0.74
    AnchorStyles
    -0.70
     nahilalakip
    -0.69
     ſtill
    -0.68
    ^(@)
    -0.67
     ſeveral
    -0.66
     ModelExpression
    -0.65
    POSITIVE LOGITS
     BorderRadius
    0.60
     scale
    0.46
    MethodManager
    0.45
     Sen
    0.44
    UnknownFieldSet
    0.44
    lanmış
    0.44
     a
    0.43
    rospy
    0.42
    áci
    0.42
     TextStyle
    0.41
    Activations Density 1.063%

    No Known Activations