INDEX

Explanations

mentions of correctness and alternatives

oai_token-act-pair · gemini-2.0-flash

accurate

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

set

-0.66

ing

-0.64

work

-0.55

but

-0.54

-0.52

ting

-0.50

my

-0.50

way

-0.50

 versus

-0.50

line

-0.49

POSITIVE LOGITS

 שוליים

1.04

AddTagHelper

1.01

 Мексичка

1.00

WindowConstants

0.98

مصادر

0.96

 समीक्षक

0.94

ividual

0.94

 مشين

0.93

 חיצוניים

0.92

 Normdatei

0.91

Activations Density 2.853%

mentions of correctness and alternatives

accurate

No Comments

No Known Activations