INDEX

Explanations

clauses

oai_token-act-pair · gemini-2.0-flash

which

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.46

 která

-0.43

 tekem

-0.43

which

-0.42

Which

-0.42

 which

-0.40

 ktorá

-0.40

and

-0.39

POSITIVE LOGITS

 Roskov

1.23

 تضيفلها

1.18

verwijspagina

1.05

SourceChecksum

1.05

 defaultstate

0.96

BufferException

0.94

 Himo

0.92

 незавершена

0.91

 Савезне

0.91

LabelTagHelper

0.91

Activations Density 3.105%

clauses

which

No Comments

No Known Activations