INDEX

Explanations

the word "Source"

oai_token-act-pair · gemini-2.0-flash

Source

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

posedge

-1.03

+#+#

-0.90

oredCriteria

-0.86

 فريبيس

-0.83

 Normdatei

-0.82

Tikang

-0.79

endphp

-0.78

ArgsConstructor

-0.78

__':

-0.78

sidemargin

-0.77

POSITIVE LOGITS

 kerja

0.43

 fuente

0.43

 links

0.41

 source

0.40

 link

0.39

 sources

0.38

 fuentes

0.37

एँ

0.37

ian

0.36

íncipe

0.35

Activations Density 0.164%

the word "Source"

Source

No Comments

No Known Activations