© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6215
    Prev
    Next
    INDEX
    Explanations

    hedging language and discussion of assumptions and risk.

    oai_token-act-pair · gemini-2.0-flash

    concepts related to limits or boundaries

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

    beyond/outside

    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
    ngdoc
    -0.75
    #+#
    -0.70
     actionMode
    -0.67
    Personendaten
    -0.67
     CWE
    -0.66
     eventdata
    -0.60
     SafeMath
    -0.59
     MonoBehaviour
    -0.59
    noinspection
    -0.57
    WSGI
    -0.54
    POSITIVE LOGITS
     beyond
    2.13
    beyond
    1.95
     Beyond
    1.82
    Beyond
    1.73
     BEYOND
    1.68
     outside
    1.54
    Outside
    1.41
     Outside
    1.39
    outside
    1.37
     out
    1.24
    Activations Density 2.280%

    No Known Activations