INDEX

Explanations

words used to make recommendations or express opinions about food, restaurants, or places

oai_token-act-pair · gemini-2.0-flash

reviews

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

lamabad

-0.73

®:

-0.56

-------------</

-0.56

Петербург

-0.54

</b>

-0.52

Петер

-0.51

 gekomen

-0.50

 Unidas

-0.50

URBANA

-0.49

 keli

-0.49

POSITIVE LOGITS

 समीक्षाओं

0.69

 initComponents

0.66

Enjoyed

0.62

ReusableCell

0.60

InstanceState

0.60

 архивлан

0.60

LikeLike

0.59

сторія

0.59

 MainAxisSize

0.58

τηση

0.57

Activations Density 1.688%

words used to make recommendations or express opinions about food, restaurants, or places

reviews

No Comments

No Known Activations