© 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. 7170
    Prev
    Next
    INDEX
    Explanations

    language associated with a person overcoming a challenge

    oai_token-act-pair · gemini-2.0-flash

    the word 'on'

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

    doing something alone

    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
     own
    -2.09
     Own
    -1.73
    Own
    -1.64
    own
    -1.61
     OWN
    -1.36
     owne
    -1.32
     eigenen
    -1.30
     eigene
    -1.30
     propia
    -1.30
     propio
    -1.24
    POSITIVE LOGITS
     on
    1.59
     On
    0.84
    On
    0.83
     на
    0.71
     على
    0.67
    on
    0.67
     auf
    0.67
     trên
    0.65
     ON
    0.63
     pada
    0.60
    Activations Density 0.889%

    No Known Activations