INDEX

Explanations

terms related to software licensing and legal code.

oai_token-act-pair · gemini-2.0-flash

reflexive pronouns

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

 your

-1.80

 yourself

-1.80

 yourselves

-1.55

your

-1.55

Your

-1.31

 youre

-1.23

yourself

-1.21

you

-1.20

 Your

-1.18

 Yourself

-1.12

POSITIVE LOGITS

 myself

1.07

myself

1.00

 ourselves

0.99

themselves

0.84

 themselves

0.76

 Myself

0.75

am

0.71

my

0.71

 dirinya

0.71

')->

0.70

Activations Density 2.095%

terms related to software licensing and legal code.

reflexive pronouns

No Comments

No Known Activations