© 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. 8321
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to crime, violence, medical examinations and portability

    oai_token-act-pair · gemini-2.0-flash

    the word 'inside'

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

    inside

    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
     Италијани
    -0.75
     виправивши
    -0.66
     utafitiHapana
    -0.65
     autorytatywna
    -0.65
    Autoritní
    -0.65
     Vikipedi
    -0.64
    ✨:
    -0.63
    ンダント
    -0.62
    :✨
    -0.61
     '\\;'
    -0.61
    POSITIVE LOGITS
     inside
    1.34
    inside
    1.17
    Inside
    1.12
     Inside
    1.09
     INSIDE
    1.01
     dentro
    0.98
     into
    0.96
     داخل
    0.92
    interno
    0.86
     dans
    0.82
    Activations Density 2.523%

    No Known Activations