INDEX

Explanations

the possessive form of 'it'

oai_token-act-pair · gemini-2.0-flash

representative

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

Hentet

-0.60

kwds

-0.48

joner

-0.48

zej

-0.48

unknownFields

-0.47

ⓘ

-0.47

Demografie

-0.47

Билгалдахарш

-0.46

</thead>

-0.45

halb

-0.45

POSITIVE LOGITS

 representative

1.38

 representatives

1.30

representative

1.28

represent

1.25

 Representative

1.16

Representative

1.13

 REPRESENT

1.10

 rappresent

1.10

 representa

1.09

 representante

1.07

Activations Density 1.983%

the possessive form of 'it'

representative

No Comments

No Known Activations