INDEX

Explanations

words and phrases associated with archeology

oai_token-act-pair · gemini-2.0-flash

historical people and cultures

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



-0.67

ricist

-0.60

LabelTagHelper

-0.55

 HasFactory

-0.54

öhe

-0.52

 jScrollPane

-0.52

 encephal

-0.50

SOUNDBITE

-0.49

سری

-0.47

ribusi

-0.47

POSITIVE LOGITS

 autorytatywna

0.68

 pinulongan

0.54

хьтан

0.51

protoc

0.51

AddTagHelper

0.51

antMatchers

0.50

[]:

0.50

عداد

0.49

enuto

0.47

MO

0.47

Activations Density 0.804%

words and phrases associated with archeology

historical people and cultures

No Comments

No Known Activations