INDEX

Explanations

words and phrases relating to bartering or misidentification of one thing for another.

oai_token-act-pair · gemini-2.0-flash

"for"

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

gonic

-0.82

\{\\

-0.76

WithIOException

-0.75

GEBURTSDATUM

-0.70

MemoryWarning

-0.66

 eventdata

-0.65

UpInside

-0.65

DockStyle

-0.65

>{@

-0.64

istoitu

-0.63

POSITIVE LOGITS

for

1.40

for

1.12

FOR

0.81

For

0.79

For

0.75

 för

0.73

 voor

0.72

 für

0.70

 за

0.68

 pentru

0.68

Activations Density 1.167%

words and phrases relating to bartering or misidentification of one thing for another.

"for"

No Comments

No Known Activations