INDEX

Explanations

symbols and notation used within mathematical equations or expressions

oai_token-act-pair · gemini-2.0-flash

punctuation

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

 meaning

-0.97

meaning

-0.75

Meaning

-0.73

 Meaning

-0.69

 ossia

-0.57

 Namely

-0.57

-0.55

 Leading

-0.54

StructEnd

-0.54

 consisting

-0.54

POSITIVE LOGITS

ourite

0.56

litude

0.52

bootstrapcdn

0.52

ègre

0.50

 fjor

0.50

ötzlich

0.50

ofday

0.49

záll

0.49

ịnh

0.48

dF

0.48

Activations Density 20.062%

symbols and notation used within mathematical equations or expressions

punctuation

No Comments

No Known Activations