INDEX

Explanations

words that could be part of a news article or story

oai_token-act-pair · gemini-2.0-flash

not the only option

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DebuggerNonUser

-0.49

cession

-0.40

 nifer

-0.39

 leksikon

-0.38

uelve

-0.37

техни

-0.36

 Question

-0.36

tahui

-0.35

end

-0.35

leave

-0.35

POSITIVE LOGITS

 AssemblyCulture

0.94

tagHelperRunner

0.92

########.

0.83

AntiForgeryToken

0.83

تقاوى

0.80

endphp

0.78

+#+#

0.77

MigrationBuilder

0.73

oredCriteria

0.73

ResumeLayout

0.72

Activations Density 43.287%

words that could be part of a news article or story

not the only option

No Comments

No Known Activations