INDEX

Explanations

words and phrases written in all capital letters

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_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Népesség

-0.66

MemoryWarning

-0.61

Архівовано

-0.59

<>

-0.56

 שוליים

-0.54

featureID

-0.54

ArgsConstructor

-0.52

InputBorder

-0.52

getExtras

-0.51

 bArr

-0.51

POSITIVE LOGITS

For

2.42

For

2.31

FOR

1.96

FOR

1.83

for

1.30

ForRow

1.13

 För

1.09

 Für

0.99

Für

0.95

 Pentru

0.94

Activations Density 13.366%

words and phrases written in all capital letters

for

No Comments

No Known Activations