© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16261
    Prev
    Next
    INDEX
    Explanations

    instances of "I am", "I do", and other expressions of personal opinion or caring

    oai_token-act-pair · gemini-2.0-flash

    Expressing concerns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     any
    -0.56
     "@/
    -0.49
    }*/
    -0.45
    __':
    -0.44
     either
    -0.44
     their
    -0.44
    ecycle
    -0.43
    ".$_
    -0.42
    Même
    -0.42
    OLOGIES
    -0.42
    POSITIVE LOGITS
    دانشنامهٔ
    0.67
    uchtigkeit
    0.64
    Collegamenti
    0.60
     כן
    0.58
    évaluateur
    0.57
    ivasan
    0.56
     esternos
    0.56
     متعلقه
    0.55
    #
    0.55
    tonode
    0.54
    Activations Density 1.827%

    No Known Activations