INDEX

Explanations

words and phrases associated with problem-solving, innovation, and working together toward a goal.

oai_token-act-pair · gemini-2.0-flash

Non-English words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 einem

-0.71

another

-0.71

 another

-0.70

 unui

-0.68

Another

-0.67

 eines

-0.65

 unei

-0.61

 Another

-0.60

an

-0.60

 seorang

-0.59

POSITIVE LOGITS

Personensuche

0.89

 disambiguazione

0.78

ArrowToggle

0.77

expandindo

0.75

 Meksiku

0.73

rawDesc

0.73

 ujednoznacz

0.71

rrggbb

0.70

argout

0.69

 المعيارى

0.66

Activations Density 7.910%

words and phrases associated with problem-solving, innovation, and working together toward a goal.

Non-English words

No Comments

No Known Activations