INDEX

Explanations

code snippets and programming language syntax

oai_token-act-pair · gemini-2.0-flash

Numbers

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

 ostavi

-0.56

PropertyChanging

-0.54

addKeyListener

-0.51

íncia

-0.50

 يتيمه

-0.49

thâu

-0.48

NewGuid

-0.48

oprecipitation

-0.48

czyny

-0.47

 positifs

-0.47

POSITIVE LOGITS

 forty

1.20

 sixty

1.20

 seventy

1.16

 thirty

1.16

 Thirty

1.12

 fifty

1.10

 nineteen

1.09

forty

1.09

 twenty

1.09

Activations Density 14.881%

code snippets and programming language syntax

Numbers

No Comments

No Known Activations