INDEX

Explanations

phrases that indicate an opinion or a guess by someone

oai_token-act-pair · gemini-2.0-flash

Uncertainty or conjecture

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 myſelf

-0.73

 bogotá

-0.68

 Theſe

-0.66

 itſelf

-0.66

 Chriſt

-0.65

 reaſon

-0.65

 againſt

-0.65

ſelf

-0.63

 Jefus

-0.63

 Conſ

-0.63

POSITIVE LOGITS

 typelib

0.65

expandindo

0.64

reportWebVitals

0.62

 disambiguazione

0.59

ConstraintMaker

0.59

 HasFactory

0.58

 समीक्षक

0.57

AttributeSet

0.57

ECONDS

0.57

 '\\;'

0.55

Activations Density 1.360%

phrases that indicate an opinion or a guess by someone

Uncertainty or conjecture

No Comments

No Known Activations