INDEX

Explanations

the word "for" or phrases that include "first" or "one of"

oai_token-act-pair · gemini-2.0-flash

first

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

expandindo

-0.82

Билгалдахарш

-0.77

RectangleBorder

-0.76

ViewImports

-0.75

DotNetBar

-0.70

 للاسماء

-0.69

SharedDtor

-0.68

RegistryLite

-0.66

 незавершена

-0.66

 MainAxisSize

-0.66

POSITIVE LOGITS

 first

2.77

first

2.42

First

1.91

 FIRST

1.82

 First

1.75

FIRST

1.70

 ﬁrst

1.66

 primero

1.55

 primeiro

1.53

 primera

1.52

Activations Density 2.645%

the word "for" or phrases that include "first" or "one of"

first

No Comments

No Known Activations

the word "for" or phrases that include "first" or "one of"

first

No Comments

No Known Activations