INDEX

Explanations

words related to making choices in positive reviews or crafting and creating

oai_token-act-pair · gemini-2.0-flash

blogs

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-0.93

 occaf

-0.67

 وتسجيلات

-0.66

Efq

-0.63

 fevere

-0.63

stdc

-0.61

 preoc

-0.60

 végétale

-0.60

+#+#

-0.57

publicain

-0.57

POSITIVE LOGITS

enumi

0.59

IUrlHelper

0.52

ň

0.46

جمعیت

0.45

 przypad

0.43

PullParser

0.42

 faudra

0.42

bridi

0.41

 toimi

0.41

raborty

0.40

Activations Density 0.706%

words related to making choices in positive reviews or crafting and creating

blogs

No Comments

No Known Activations