INDEX

Explanations

words associated with movement and direction

oai_token-act-pair · gemini-2.0-flash

directional words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

\{\\

-0.87

 nahilalakip

-0.85

 autorytatywna

-0.72

ViewFeatures

-0.70

 bezeichneter

-0.70

SequentialGroup

-0.69

findpost

-0.68

TZ

-0.67

")));

-0.67

 otomatig

-0.67

POSITIVE LOGITS

 across

0.76

across

0.68

 over

0.68

 ACROSS

0.59

 Across

0.59

Across

0.57

over

0.51

Over

0.42

tag

0.42

 dispersion

0.41

Activations Density 1.652%

words associated with movement and direction

directional words

No Comments

No Known Activations