INDEX

Explanations

dates in the 1900s

oai_token-act-pair · gemini-2.0-flash

1

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

(!__

-0.67

MessageOf

-0.66

 незавершена

-0.66

rophes

-0.65

 ModelExpression

-0.65

cagon

-0.64

oneofs

-0.64

ContentAsync

-0.59

 StringTokenizer

-0.58

igshid

-0.55

POSITIVE LOGITS

halter

0.50

 Executive

0.47

 Halter

0.45

nü

0.45

'])){

0.45

gebracht

0.45

IELD

0.44

 Sham

0.44

lati

0.44

)][

0.44

Activations Density 0.268%

dates in the 1900s

1

No Comments

No Known Activations